3D Object Reconstruction
42 papers with code • 2 benchmarks • 3 datasets
Image: Choy et al
LibrariesUse these libraries to find 3D Object Reconstruction models and implementations
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).
Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e. g., table legs) from different coarse 3D volumes to obtain a fused 3D volume.
Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
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.
We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.
A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume.