OCTScenes contains 5000 tabletop scenes with a total of 15 everyday objects. Each scene is captured in 60 frames covering a 360-degree perspective.
OCTScenes-A dataset, the 0--3099 scenes without segmentation annotation are for training, while the 3100--3199 scenes with segmentation annotation can be used for testing. In the OCTScenes-B dataset, the 0--4899 scenes without segmentation annotation are for training, while the 4900--4999 scenes with segmentation annotation can be used for testing.
Paper | Code | Results | Date | Stars |
---|