Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields

TL;DR

Hyb-NeRF introduces a multi-resolution hybrid encoding approach for neural radiance fields that enhances rendering speed, reduces memory usage, and improves view synthesis quality by combining coarse and fine resolution strategies.

Contribution

It proposes a novel hybrid encoding method that integrates learnable positional features and hash-based grids for efficient and high-quality neural scene reconstruction.

Findings

Faster rendering speed compared to previous methods

Lower memory footprint while maintaining high quality

Better rendering quality on synthetic and real-world datasets

Abstract

Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume rendering integral, making it slow to train. Caching NeRFs into explicit data structures can effectively enhance rendering speed but at the cost of higher memory usage. To address these issues, we present Hyb-NeRF, a novel neural radiance field with a multi-resolution hybrid encoding that achieves efficient neural modeling and fast rendering, which also allows for high-quality novel view synthesis. The key idea of Hyb-NeRF is to represent the scene using different encoding strategies from coarse-to-fine resolution levels. Hyb-NeRF exploits memory-efficiency learnable positional features at coarse resolutions and the fast optimization speed and local details of hash-based feature grids at fine resolutions. In addition, to further boost performance, we embed cone tracing-based features in our learnable positional encoding that eliminates encoding ambiguity and reduces aliasing artifacts. Extensive experiments on both synthetic and real-world datasets show that Hyb-NeRF achieves faster rendering speed with better rending quality and even a lower memory footprint in comparison to previous state-of-the-art methods.