What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Optics
- Computer vision
Srinivasa G. Narasimhan focuses on Artificial intelligence, Computer vision, Haze, Image restoration and Image processing.
His research on Artificial intelligence often connects related areas such as Snow.
When carried out as part of a general Computer vision research project, his work on Object detection is frequently linked to work in Process, therefore connecting diverse disciplines of study.
His Haze research is multidisciplinary, incorporating perspectives in Diffuse sky radiation, Atmosphere, Atmospheric optics and Machine vision.
Srinivasa G. Narasimhan has included themes like Polarizer and Chromatic scale in his Diffuse sky radiation study.
Srinivasa G. Narasimhan has researched Image restoration in several fields, including RGB color model, Light scattering, Scattering and Video camera.
His most cited work include:
- Contrast restoration of weather degraded images (1041 citations)
- Vision and the Atmosphere (816 citations)
- Instant dehazing of images using polarization (586 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Computer vision, Optics, Pixel and Scattering are his primary areas of study.
His research on Artificial intelligence frequently links to adjacent areas such as Haze.
His Haze study also includes
- Diffuse sky radiation which intersects with area such as Chromatic scale and Segmentation,
- Atmospheric optics together with Snow.
His work in Computer vision tackles topics such as Computer graphics which are related to areas like Shadow and Active vision.
His work on Light beam, Lens and Focal length as part of his general Optics study is frequently connected to Materials science, thereby bridging the divide between different branches of science.
His Pixel study combines topics from a wide range of disciplines, such as Image quality, Brightness, High dynamic range and Color image.
He most often published in these fields:
- Artificial intelligence (71.43%)
- Computer vision (68.42%)
- Optics (14.29%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (71.43%)
- Computer vision (68.42%)
- Optics (14.29%)
In recent papers he was focusing on the following fields of study:
Srinivasa G. Narasimhan spends much of his time researching Artificial intelligence, Computer vision, Optics, Computational photography and RGB color model.
In general Artificial intelligence, his work in Projector is often linked to Event linking many areas of study.
His Computer vision study integrates concerns from other disciplines, such as Visualization, Deep learning and Detector.
His work in the fields of Optics, such as Focal length, Light beam, Scattering and Lens, intersects with other areas such as Materials science.
The concepts of his RGB color model study are interwoven with issues in Texture, Polygon mesh, Rendering and Reflection mapping.
As a part of the same scientific study, Srinivasa G. Narasimhan usually deals with the Pixel, concentrating on Video camera and frequently concerns with Image resolution.
Between 2018 and 2021, his most popular works were:
- A Theory of Fermat Paths for Non-Line-Of-Sight Shape Reconstruction (47 citations)
- Neural RGB®D Sensing: Depth and Uncertainty From a Video Camera (42 citations)
- Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks (17 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Optics
- Computer vision
His primary scientific interests are in Artificial intelligence, Computer vision, Pixel, Computational photography and Video camera.
His studies in Artificial intelligence integrate themes in fields like Specular reflection and Viewpoints.
The concepts of his Specular reflection study are interwoven with issues in Epipolar geometry, Subsurface scattering, Projector and Normal.
His work on Iterative reconstruction as part of general Computer vision research is frequently linked to Event, thereby connecting diverse disciplines of science.
The study incorporates disciplines such as Light scattering, Radiative transfer, Optics and Computation in addition to Computational photography.
His research integrates issues of Image resolution, 3D reconstruction, Deep learning and RGB color model in his study of Video camera.
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.
