×

3D-R2N2

swMATH ID: 42746
Software Authors: Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese
Description: 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction. Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The network learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data. Our network takes in one or more images of an object instance from arbitrary viewpoints and outputs a reconstruction of the object in the form of a 3D occupancy grid. Unlike most of the previous works, our network does not require any image annotations or object class labels for training or testing. Our extensive experimental analysis shows that our reconstruction framework i) outperforms the state-of-the-art methods for single view reconstruction, and ii) enables the 3D reconstruction of objects in situations when traditional SFM/SLAM methods fail (because of lack of texture and/or wide baseline).
Homepage: https://arxiv.org/abs/1604.00449
Source Code: https://github.com/chrischoy/3D-R2N2
Dependencies: Python
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Artificial Intelligence; arXiv_cs.AI; 3D-R2N2; 3D Object Reconstruction; multi-view; econstruction; recurrent neural network
Related Software: ShapeNet; PointNet; Adam; Pixel2Mesh; OpenDR; SoftRas; PyTorch; TensorFlow; DeepSDF; Theano; Make3D; MeshLab; OctNet; Tensor2Tensor; pix2pix; CycleGAN; Kaolin; DensePose; SynSin; Mitsuba
Cited in: 8 Publications

Standard Articles

1 Publication describing the Software Year
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese
2016

Citations by Year