DeepAI AI Chat
Log In Sign Up

A Simple and Scalable Shape Representation for 3D Reconstruction

by   Mateusz Michalkiewicz, et al.

Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-decoder model usually applied in voxel space. However, this often scales very poorly with the resolution limiting the effectiveness of these models. Several sophisticated alternatives for decoding to 3D shapes have been proposed typically relying on complex deep learning architectures for the decoder model. In this work, we show that this additional complexity is not necessary, and that we can actually obtain high quality 3D reconstruction using a linear decoder, obtained from principal component analysis on the signed distance function (SDF) of the surface. This approach allows easily scaling to larger resolutions. We show in multiple experiments that our approach is competitive with state-of-the-art methods. It also allows the decoder to be fine-tuned on the target task using a loss designed specifically for SDF transforms, obtaining further gains.


page 1

page 4

page 9


Multi-Modal Face Stylization with a Generative Prior

In this work, we introduce a new approach for artistic face stylization....

Loss Landscapes of Regularized Linear Autoencoders

Autoencoders are a deep learning model for representation learning. When...

Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes

We present an Adaptive Octree-based Convolutional Neural Network (Adapti...

Probabilistic 3D surface reconstruction from sparse MRI information

Surface reconstruction from magnetic resonance (MR) imaging data is indi...

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

We treat shape co-segmentation as a representation learning problem and ...

What Do Single-view 3D Reconstruction Networks Learn?

Convolutional networks for single-view object reconstruction have shown ...