DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer
3D scene understanding for robotic applications exhibits a unique set of requirements including real-time inference, object-centric latent representation learning, accurate 6D pose estimation and 3D reconstruction of objects. Current methods for scene understanding typically rely on a combination of...
Príomhchruthaitheoirí: | Wu, Y, Sáez de Ocáriz Borde, H, Collins, J, Jones, OP, Posner, I |
---|---|
Formáid: | Journal article |
Teanga: | English |
Foilsithe / Cruthaithe: |
IEEE
2024
|
Míreanna comhchosúla
Míreanna comhchosúla
-
APEX: Unsupervised, object-centric scene segmentation and tracking for robot manipulation
de réir: Wu, Y, et al.
Foilsithe / Cruthaithe: (2021) -
GENESIS: generative scene inference and sampling of object-centric latent representations
de réir: Engelcke, M, et al.
Foilsithe / Cruthaithe: (2020) -
Multi-view fusion-based 3D object detection for robot indoor scene perception
de réir: Wang, Li, et al.
Foilsithe / Cruthaithe: (2020) -
Multi-View Fusion-Based 3D Object Detection for Robot Indoor Scene Perception
de réir: Li Wang, et al.
Foilsithe / Cruthaithe: (2019-09-01) -
Scene-conditional 3D object stylization and composition
de réir: Zhou, J, et al.
Foilsithe / Cruthaithe: (2024)