Ray-ONet: efficient 3D reconstruction from a single RGB image
<p>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 Oc...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
British Machine Vision Association
2022
|
| Summary: | <p>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(N<sup>2</sup>). As a result, Ray-ONet achieves state-of-the-art performance on the ShapeNet benchmark with more than 20×speed-up at 128<sup>3</sup> resolution and maintains a similar memory footprint during inference.</p> |
|---|