Search Results for author:
Found 3 papers, 0 papers with code
Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints
This ability is essential for humans to identify the same object while moving and to learn from vision efficiently.
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning
The results demonstrate the shortcomings of state-of-the-art methods for learning meaningful representations from real-world data, despite their impressive performance on complex synthesis datasets.
Compositional Scene Modeling with Global Object-Centric Representations
Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
