Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI dataset.
Sagi EppelHaoping XuYi Ru WangAlán Aspuru-GuzikPublished in: CoRR (2021)
Keyphrases
- transparent objects
- topological properties
- geometrical properties
- objects represented
- rotationally symmetric
- shape variability
- visual objects
- topological features
- shape analysis
- benchmark datasets
- shape properties
- shape model
- real objects
- shape similarity
- synthetic datasets
- shape representation
- client server
- data objects
- shape recognition
- invariant properties
- multiple objects
- d objects
- e learning
- computer vision