We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes.
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).
#5 best model for 3D Reconstruction on Data3D−R2N2
Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones.
In this paper, we address the problem of 3D object mesh reconstruction from RGB videos.
In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.
We consider the problem of scaling deep generative shape models to high-resolution.
#2 best model for 3D Object Reconstruction on Data3D−R2N2
Mesh models are a promising approach for encoding the structure of 3D objects.
Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of 256^3 by recovering the occluded/missing regions.
Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
#3 best model for 3D Reconstruction on Data3D−R2N2 (using extra training data)