What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Optics
Hendrik P. A. Lensch mainly investigates Computer vision, Artificial intelligence, Computer graphics, Reflectivity and Iterative reconstruction.
His work in Rendering, Motion blur, Photometric stereo, Normal mapping and Texture filtering is related to Computer vision.
His study looks at the intersection of Rendering and topics like Image based with Point light source.
His Computer graphics study deals with Computational photography intersecting with Image quality, Computer hardware and Open architecture.
His work deals with themes such as Image, Set, Remote sensing and Contrast, which intersect with Reflectivity.
His research integrates issues of Signal-to-noise ratio, Pixel, Image sensor and Gaussian noise in his study of Iterative reconstruction.
His most cited work include:
- Image-based reconstruction of spatial appearance and geometric detail (272 citations)
- Dual photography (242 citations)
- The Frankencamera: an experimental platform for computational photography (145 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Computer vision, Computer graphics, Rendering and Reflectivity.
His is doing research in Object, Deep learning, Artificial neural network, Ground truth and Convolutional neural network, both of which are found in Artificial intelligence.
His Computer vision study combines topics in areas such as Bidirectional reflectance distribution function and Graphics.
Hendrik P. A. Lensch interconnects Subsurface scattering and Measure in the investigation of issues within Graphics.
His research on Computer graphics frequently links to adjacent areas such as Visualization.
His research on Rendering often connects related areas such as Texture mapping.
He most often published in these fields:
- Artificial intelligence (58.10%)
- Computer vision (49.52%)
- Computer graphics (26.19%)
What were the highlights of his more recent work (between 2015-2020)?
- Artificial intelligence (58.10%)
- Computer vision (49.52%)
- Deep learning (4.76%)
In recent papers he was focusing on the following fields of study:
Hendrik P. A. Lensch spends much of his time researching Artificial intelligence, Computer vision, Deep learning, Artificial neural network and Algorithm.
His Artificial intelligence research integrates issues from Machine learning and Pattern recognition.
His Computer vision study combines topics from a wide range of disciplines, such as Computer graphics, Robustness and Graphics.
His research in Graphics intersects with topics in View synthesis, Joint and Reflectivity.
His Artificial neural network research incorporates elements of Estimation theory, External Data Representation and Computational science.
His studies deal with areas such as Sampling, Importance sampling, Overfitting and Complex dynamics as well as Algorithm.
Between 2015 and 2020, his most popular works were:
- Learning Blind Motion Deblurring (66 citations)
- Infrared Colorization Using Deep Convolutional Neural Networks (57 citations)
- Self-supervised regrasping using spatio-temporal tactile features and reinforcement learning (50 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Optics
His main research concerns Artificial intelligence, Computer vision, Artificial neural network, Deblurring and Deep learning.
His Artificial intelligence study frequently draws connections between adjacent fields such as Pattern recognition.
Hendrik P. A. Lensch combines topics linked to Graphics with his work on Computer vision.
His Graphics research is multidisciplinary, relying on both Bidirectional reflectance distribution function, Reflectivity, View synthesis, Rendering and Joint.
His study explores the link between Deblurring and topics such as Motion blur that cross with problems in Image restoration and Iterative reconstruction.
His Deep learning research includes elements of Ranking, Information retrieval and Feature vector.
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.
