What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
Andreas Geiger mainly focuses on Artificial intelligence, Computer vision, Object detection, Visual odometry and Robustness.
The study of Artificial intelligence is intertwined with the study of Pattern recognition in a number of ways.
Many of his studies on Computer vision apply to Benchmark as well.
Andreas Geiger studied Visual odometry and Odometry that intersect with Computer stereo vision, Frame rate, Template matching and Stereo camera.
Andreas Geiger has researched Robustness in several fields, including Image sensor, Image registration and Grayscale.
His studies deal with areas such as Optical flow and Robotics as well as Stereo cameras.
His most cited work include:
- Are we ready for autonomous driving? The KITTI vision benchmark suite (5548 citations)
- Vision meets robotics: The KITTI dataset (3500 citations)
- Object scene flow for autonomous vehicles (947 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, 3D reconstruction, Pattern recognition and Segmentation.
His research on Artificial intelligence frequently connects to adjacent areas such as Machine learning.
While the research belongs to areas of Computer vision, Andreas Geiger spends his time largely on the problem of Visual odometry, intersecting his research to questions surrounding Odometry, Motion planning and Stereo cameras.
The study incorporates disciplines such as Voxel, Surface, Probabilistic logic and Iterative reconstruction in addition to 3D reconstruction.
His Pattern recognition study integrates concerns from other disciplines, such as RGB color model, Artificial neural network, Representation and Invariant.
The Optical flow estimation research Andreas Geiger does as part of his general Optical flow study is frequently linked to other disciplines of science, such as Discrete optimization, therefore creating a link between diverse domains of science.
He most often published in these fields:
- Artificial intelligence (90.74%)
- Computer vision (51.23%)
- 3D reconstruction (25.31%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (90.74%)
- Computer vision (51.23%)
- Object (11.73%)
In recent papers he was focusing on the following fields of study:
Andreas Geiger mostly deals with Artificial intelligence, Computer vision, Object, Rendering and 3D reconstruction.
His Artificial intelligence study combines topics in areas such as Machine learning and Pattern recognition.
His study ties his expertise on Representation together with the subject of Computer vision.
Andreas Geiger has included themes like Voxel and Pose in his Rendering study.
His work in 3D reconstruction addresses subjects such as Iterative reconstruction, which are connected to disciplines such as Implicit function and Polygon mesh.
His Benchmark study combines topics from a wide range of disciplines, such as Robotics and Synthetic data.
Between 2019 and 2021, his most popular works were:
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision (106 citations)
- Convolutional Occupancy Networks (58 citations)
- GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis (44 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary scientific interests are in Artificial intelligence, Computer vision, 3D reconstruction, Task analysis and Pattern recognition.
His Artificial intelligence study frequently draws connections between related disciplines such as State.
His Computer vision research is multidisciplinary, incorporating elements of Representation and Generative model.
His work carried out in the field of 3D reconstruction brings together such families of science as Point cloud, Iterative reconstruction and Pattern recognition.
His Point cloud research is multidisciplinary, relying on both Contrast, Robotics and Synthetic data.
Video tracking and Data mining is closely connected to Benchmark in his research, which is encompassed under the umbrella topic of Pattern recognition.
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.
