What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Geometry
His main research concerns Artificial intelligence, Computer vision, Segmentation, Pattern recognition and Object.
His research in Artificial intelligence focuses on subjects like Machine learning, which are connected to Procedural modeling.
The study incorporates disciplines such as Visualization, Feature learning and Computer graphics in addition to Computer vision.
His Segmentation research is multidisciplinary, incorporating perspectives in Polygon mesh, Coordinate system and Surface.
His research investigates the connection between Pattern recognition and topics such as Image resolution that intersect with issues in Solid modeling.
Thomas Funkhouser has included themes like Taxonomy, Information retrieval and Benchmark in his Object study.
His most cited work include:
- ShapeNet: An Information-Rich 3D Model Repository (1726 citations)
- Shape distributions (1442 citations)
- The Princeton Shape Benchmark (1257 citations)
What are the main themes of his work throughout his whole career to date?
Thomas Funkhouser focuses on Artificial intelligence, Computer vision, Segmentation, Computer graphics and Pattern recognition.
Artificial intelligence is often connected to Machine learning in his work.
Thomas Funkhouser interconnects Deep learning, Computer graphics and Benchmark in the investigation of issues within Computer vision.
His studies examine the connections between Segmentation and genetics, as well as such issues in Polygon mesh, with regards to Algorithm and Surface.
His work on Shape analysis expands to the thematically related Computer graphics.
In general Pattern recognition, his work in Active shape model is often linked to Probability distribution and Context linking many areas of study.
He most often published in these fields:
- Artificial intelligence (60.00%)
- Computer vision (41.43%)
- Segmentation (12.38%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (60.00%)
- Computer vision (41.43%)
- Pixel (10.00%)
In recent papers he was focusing on the following fields of study:
Thomas Funkhouser mostly deals with Artificial intelligence, Computer vision, Pixel, Representation and RGB color model.
Within one scientific family, Thomas Funkhouser focuses on topics pertaining to Pattern recognition under Artificial intelligence, and may sometimes address concerns connected to Interpolation.
His Computer vision research includes themes of End-to-end principle and Point.
His Pixel research is multidisciplinary, incorporating elements of Surface and Normal.
His Representation study combines topics in areas such as Embedding, Polygon mesh, Implicit function and Surface reconstruction.
The Object study which covers Contrast that intersects with Curse of dimensionality.
Between 2017 and 2021, his most popular works were:
- Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching (177 citations)
- Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning (173 citations)
- Deep Depth Completion of a Single RGB-D Image (140 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Geometry
His primary areas of investigation include Artificial intelligence, Computer vision, Pixel, RGB color model and Representation.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Surface reconstruction and Pattern recognition.
His Computer vision research integrates issues from SMT placement equipment and Robotics.
His research investigates the connection with Pixel and areas like Inpainting which intersect with concerns in Image resolution.
His research integrates issues of Coplanarity, Margin, Matching, Planar and Benchmark in his study of RGB color model.
His Representation study also includes fields such as
- Embedding, which have a strong connection to Autoencoder, Grid and Regular grid,
- Implicit function and related Computer graphics and Graphics.
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.
