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($N^2$). As a result, Ray-ONet achieves state-of-the-art performance on the ShapeNet benchmark with more than 20$\times$ speed-up at $128^3$ resolution and maintains a similar memory footprint during inference.

arXiv commentaccepted in BMVC 2021

References in corpus (7)

• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
• PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
• Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
• FroDO: From Detections to 3D Objects
• Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction