Neural NeRF Compression
This addresses storage issues for users of 3D scene reconstruction with NeRFs, but it is incremental as it builds on existing grid-based NeRF methods.
The paper tackles the storage overhead problem in grid-based Neural Radiance Fields (NeRFs) by proposing a novel compression method using neural compression with an importance-weighted rate-distortion objective and sparse entropy model, achieving superior compression efficacy and reconstruction quality compared to existing works.
Neural Radiance Fields (NeRFs) have emerged as powerful tools for capturing detailed 3D scenes through continuous volumetric representations. Recent NeRFs utilize feature grids to improve rendering quality and speed; however, these representations introduce significant storage overhead. This paper presents a novel method for efficiently compressing a grid-based NeRF model, addressing the storage overhead concern. Our approach is based on the non-linear transform coding paradigm, employing neural compression for compressing the model's feature grids. Due to the lack of training data involving many i.i.d scenes, we design an encoder-free, end-to-end optimized approach for individual scenes, using lightweight decoders. To leverage the spatial inhomogeneity of the latent feature grids, we introduce an importance-weighted rate-distortion objective and a sparse entropy model employing a masking mechanism. Our experimental results validate that our proposed method surpasses existing works in terms of grid-based NeRF compression efficacy and reconstruction quality.