UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields

TL;DR

UNeRF introduces a U-shaped network architecture that shares computations across neighboring samples, significantly reducing training memory and time for neural radiance fields while maintaining or improving synthesis quality.

Contribution

The paper proposes a novel UNeRF architecture that exploits sample redundancy, reducing resource requirements and improving accuracy in neural radiance field training and inference.

Findings

Reduces memory footprint during training.

Improves novel view synthesis quality.

Speeds up training and inference processes.

Abstract

Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction, with applications ranging from large static scenes to dynamic human motion. However, the increased resolution and model-free nature of such neural fields come at the cost of high training times and excessive memory requirements. Recent advances improve the inference time by using complementary data structures yet these methods are ill-suited for dynamic scenes and often increase memory consumption. Little has been done to reduce the resources required at training time. We propose a method to exploit the redundancy of NeRF's sample-based computations by partially sharing evaluations across neighboring sample points. Our UNeRF architecture is inspired by the UNet, where spatial resolution is reduced in the middle of the network and information is shared between adjacent samples. Although this change violates the strict and conscious separation of view-dependent appearance and view-independent density estimation in the NeRF method, we show that it improves novel view synthesis. We also introduce an alternative subsampling strategy which shares computation while minimizing any violation of view invariance. UNeRF is a plug-in module for the original NeRF network. Our major contributions include reduction of the memory footprint, improved accuracy, and reduced amortized processing time both during training and inference. With only weak assumptions on locality, we achieve improved resource utilization on a variety of neural radiance fields tasks. We demonstrate applications to the novel view synthesis of static scenes as well as dynamic human shape and motion.