Conference item
Ray-ONet: efficient 3D reconstruction from a single RGB image
- Abstract:
-
We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently. By predicting a series of occupancy probabilities along a ray that is back-projected from a pixel in the camera coordinate, our method Ray-ONet improves the reconstruction accuracy in comparison with Occupancy Networks (ONet), while reducing the network inference complexity to O(N2). As a result, Ray-ONet achieves state-of-the-art performance on the ShapeNet benchmark with more than 20×...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Reviewed (other)
Actions
Authors
Bibliographic Details
- Publisher:
- British Machine Vision Association Publisher's website
- Journal:
- Proceedings of the 32nd British Machine Vision Conference Journal website
- Publication date:
- 2022-01-01
- Acceptance date:
- 2021-10-15
- Event title:
- British Machine Vision Conference 2021
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1203310
- Local pid:
- pubs:1203310
- Deposit date:
- 2021-10-18
Terms of use
- Copyright holder:
- Bian et al.
- Copyright date:
- 2022
- Rights statement:
- © 2021. The copyright of this document resides with its authors.
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record