What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Mathematical analysis
Renaud Keriven spends much of his time researching Artificial intelligence, Computer vision, Robustness, Point cloud and Surface.
Renaud Keriven interconnects Geodesic and Graphics in the investigation of issues within Artificial intelligence.
Renaud Keriven combines subjects such as Energy and Boundary with his study of Computer vision.
His Robustness research is multidisciplinary, incorporating elements of Motion estimation and Image registration.
He has included themes like Real image and Variational principle in his Surface study.
His work carried out in the field of Variational principle brings together such families of science as Algorithm, Level set and Partial differential equation.
His most cited work include:
- Variational principles, surface evolution, PDEs, level set methods, and the stereo problem (387 citations)
- CURVES: Curve evolution for vessel segmentation (285 citations)
- A common formalism for the Integral formulations of the forward EEG problem (272 citations)
What are the main themes of his work throughout his whole career to date?
Renaud Keriven mainly focuses on Artificial intelligence, Computer vision, Pattern recognition, Image segmentation and Algorithm.
His study in Segmentation, Robustness, Active shape model, Level set and Image processing falls under the purview of Artificial intelligence.
His Level set study combines topics from a wide range of disciplines, such as Real image, Surface, Level set method and Variational principle.
The concepts of his Computer vision study are interwoven with issues in Polygon mesh and Geodesic.
His Pattern recognition research includes elements of Nonlinear dimensionality reduction, Cognitive neuroscience of visual object recognition and Kernel.
His biological study spans a wide range of topics, including Partial differential equation, Mathematical optimization and Inverse problem.
He most often published in these fields:
- Artificial intelligence (68.22%)
- Computer vision (51.40%)
- Pattern recognition (20.56%)
What were the highlights of his more recent work (between 2008-2013)?
- Artificial intelligence (68.22%)
- Computer vision (51.40%)
- Algorithm (16.82%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Computer vision, Algorithm, Iterative reconstruction and Outlier.
His work deals with themes such as Graph and Pattern recognition, which intersect with Artificial intelligence.
In his work, Geometric primitive and Segmentation is strongly intertwined with Polygon mesh, which is a subfield of Computer vision.
His research in Algorithm intersects with topics in Image plane, Orientation, Graph theory and Mathematical optimization.
The study incorporates disciplines such as Pipeline, Visibility and Surface reconstruction in addition to Iterative reconstruction.
The Robustness study combines topics in areas such as Delaunay triangulation and Cut.
Between 2008 and 2013, his most popular works were:
- Towards high-resolution large-scale multi-view stereo (209 citations)
- High Accuracy and Visibility-Consistent Dense Multiview Stereo (188 citations)
- Geodesic Methods in Computer Vision and Graphics (104 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Mathematical analysis
His scientific interests lie mostly in Artificial intelligence, Computer vision, Image segmentation, Point cloud and Iterative reconstruction.
His Artificial intelligence study often links to related topics such as Graphics.
As a part of the same scientific family, Renaud Keriven mostly works in the field of Computer vision, focusing on Geodesic and, on occasion, Voronoi diagram, Computer graphics, Surface and Riemannian manifold.
His studies in Image segmentation integrate themes in fields like Basis, Algorithm, Polygon mesh and Geometric primitive.
Renaud Keriven has researched Point cloud in several fields, including Delaunay triangulation, Pipeline, Surface reconstruction, Mathematical optimization and Visibility.
His study in Iterative reconstruction is interdisciplinary in nature, drawing from both Markov random field, Iterative method, Iterative refinement and 3D modeling.
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.
