Neural 3D Scene Compression via Model Compression
arXiv:2105.03120
Abstract
Rendering 3D scenes requires access to arbitrary viewpoints from the scene. Storage of such a 3D scene can be done in two ways; (1) storing 2D images taken from the 3D scene that can reconstruct the scene back through interpolations, or (2) storing a representation of the 3D scene itself that already encodes views from all directions. So far, traditional 3D compression methods have focused on the first type of storage and compressed the original 2D images with image compression techniques. With this approach, the user first decodes the stored 2D images and then renders the 3D scene. However, this separated procedure is inefficient since a large amount of 2D images have to be stored. In this work, we take a different approach and compress a functional representation of 3D scenes. In particular, we introduce a method to compress 3D scenes by compressing the neural networks that represent the scenes as neural radiance fields. Our method provides more efficient storage of 3D scenes since it does not store 2D images -- which are redundant when we render the scene from the neural functional representation.
arXiv commentStanford CS 231A Final Project, 2021. WiCV at CVPR 2021
References in corpus (8)
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- The State of Sparsity in Deep Neural Networks
- Variational Dropout Sparsifies Deep Neural Networks
- Implicit Neural Representations with Periodic Activation Functions
- Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
- Image compression optimized for 3D reconstruction by utilizing deep neural networks