What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Optics
- Computer vision
His primary areas of investigation include Artificial intelligence, Computer vision, Computer graphics, Optics and Projector.
His Artificial intelligence study frequently involves adjacent topics like Machine learning.
His Computer vision research is multidisciplinary, relying on both Lens and Photography.
His research investigates the link between Computer graphics and topics such as Augmented reality that cross with problems in Computer graphics.
Ramesh Raskar has included themes like Computational photography and Parallax in his Optics study.
His work in Projector tackles topics such as Surface which are related to areas like Transformation.
His most cited work include:
- Image-based visual hulls (845 citations)
- The office of the future: a unified approach to image-based modeling and spatially immersive displays (760 citations)
- Spatial Augmented Reality: Merging Real and Virtual Worlds (578 citations)
What are the main themes of his work throughout his whole career to date?
Ramesh Raskar spends much of his time researching Artificial intelligence, Computer vision, Computer graphics, Optics and Projector.
His research is interdisciplinary, bridging the disciplines of Machine learning and Artificial intelligence.
His Computer vision research incorporates themes from Lens, Surface and Photography.
His Computer graphics study incorporates themes from Augmented reality and Flash.
Scattering, Ray, Light scattering and Ultrashort pulse are among the areas of Optics where the researcher is concentrating his efforts.
His studies deal with areas such as Liquid-crystal display, Parallax and Stereo display as well as Light field.
He most often published in these fields:
- Artificial intelligence (55.56%)
- Computer vision (48.54%)
- Computer graphics (24.85%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (55.56%)
- Optics (23.25%)
- Machine learning (3.51%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Optics, Machine learning, Deep learning and Computer vision.
The concepts of his Artificial intelligence study are interwoven with issues in Raw data, Data science and Pattern recognition.
His studies examine the connections between Pattern recognition and genetics, as well as such issues in Overfitting, with regards to Pairwise comparison and Feature learning.
In his work, Pixel is strongly intertwined with Phase, which is a subfield of Optics.
His work blends Computer vision and Context studies together.
Ramesh Raskar usually deals with Scattering and limits it to topics linked to Photon and Medical imaging.
Between 2016 and 2021, his most popular works were:
- Advances and Open Problems in Federated Learning (571 citations)
- Accelerating Neural Architecture Search using Performance Prediction (136 citations)
- Split learning for health: Distributed deep learning without sharing raw patient data (100 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Optics
- Computer vision
Ramesh Raskar mainly investigates Artificial intelligence, Machine learning, Artificial neural network, Deep learning and Computer vision.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Replication and Identification.
His Machine learning study integrates concerns from other disciplines, such as Range and Health care.
His Artificial neural network study combines topics in areas such as Performance prediction and Labeled data, Pattern recognition.
His Deep learning research integrates issues from Stochastic gradient descent, Inference, Data science, Invariant and Data set.
His work deals with themes such as Laser and Search and rescue, which intersect with Computer vision.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
