Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image [article]

Wenjing Bian and Zirui Wang and Kejie Li and Victor Adrian Prisacariu
2021 arXiv   pre-print
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^2). As a result, Ray-ONet achieves state-of-the-art performance on the ShapeNet benchmark with more than 20× speed-up at 128^3
more » ... solution and maintains a similar memory footprint during inference.
arXiv:2107.01899v2 fatcat:yd6tjvaoe5aghmzqttagwzn7ke