More Robots are Coming: Large Multimodal Models (ChatGPT) can Solve Visually Diverse Images of Parsons Problems.
Irene HouOwen ManSophie MettilleSebastian GutierrezKenneth AngelikasStephen MacNeilPublished in: CoRR (2023)
Keyphrases
- random fields
- input image
- rigid body
- ground truth
- image retrieval
- image database
- image classification
- object recognition in computer vision
- image analysis
- image data
- image collections
- solving complex
- edge detection
- test images
- segmentation algorithm
- mathematical programming
- cooperative
- three dimensional
- computer graphics
- image processing
- robotic systems
- image features
- parametric models
- object recognition
- object models
- human visual system
- multi modal
- multiple images
- mobile robot
- three dimensional objects
- multimodal image registration