What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Geometry
Long Quan focuses on Artificial intelligence, Computer vision, Pattern recognition, Image and Real image.
The various areas that Long Quan examines in his Artificial intelligence study include Algorithm and Affine transformation.
Many of his studies on Computer vision involve topics that are commonly interrelated, such as Robustness.
His study in the field of Support vector machine also crosses realms of Markov process, Nose and Gaussian process.
His work in the fields of Image, such as Image based, overlaps with other areas such as Flexibility and Key.
His work in Real image covers topics such as Orientation which are related to areas like Point, Singular value decomposition, Algebraic number, Photogrammetry and Pose.
His most cited work include:
- Image deblurring with blurred/noisy image pairs (854 citations)
- Linear N-point camera pose determination (507 citations)
- A quasi-dense approach to surface reconstruction from uncalibrated images (325 citations)
What are the main themes of his work throughout his whole career to date?
Long Quan spends much of his time researching Artificial intelligence, Computer vision, Pattern recognition, Algorithm and Pixel.
Artificial intelligence and Affine transformation are commonly linked in his work.
His Computer vision study frequently links to adjacent areas such as Surface reconstruction.
His Pattern recognition study integrates concerns from other disciplines, such as Point cloud, Facial recognition system and Feature.
His work focuses on many connections between Structure from motion and other disciplines, such as Bundle adjustment, that overlap with his field of interest in 3D reconstruction.
His research in Real image intersects with topics in Trifocal tensor and Conic section.
He most often published in these fields:
- Artificial intelligence (77.48%)
- Computer vision (59.92%)
- Pattern recognition (17.18%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (77.48%)
- Computer vision (59.92%)
- Pattern recognition (17.18%)
In recent papers he was focusing on the following fields of study:
Long Quan mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Feature and Pixel.
His Artificial intelligence study typically links adjacent topics like Generalization.
His Image study, which is part of a larger body of work in Computer vision, is frequently linked to Code, bridging the gap between disciplines.
Long Quan interconnects Noise and Pose in the investigation of issues within Pattern recognition.
The Pixel study combines topics in areas such as Semantics, Computer vision pattern recognition, Pyramid and Test set.
His Feature extraction research includes elements of Transformation, Orientation and Image resolution.
Between 2017 and 2021, his most popular works were:
- MVSNet: Depth inference for unstructured multi-view stereo (218 citations)
- Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference (92 citations)
- GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints (86 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Geometry
Artificial intelligence, Deep learning, Computer vision, Geometry and Pattern recognition are his primary areas of study.
His Artificial intelligence study often links to related topics such as Generalization.
In his study, Depth map, Image warping and Homography is strongly linked to Inference, which falls under the umbrella field of Deep learning.
His research integrates issues of Margin and Simultaneous localization and mapping in his study of Computer vision.
His Geometry research incorporates themes from Image and Convolutional neural network.
His work in Pattern recognition tackles topics such as Point cloud which are related to areas like Correspondence problem, Outlier, Leverage, Detector and Kernel.
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.
