On Quantizing Implicit Neural Representations
This addresses compression for implicit neural representations like NeRFs, which is incremental as it builds on existing quantization methods.
The paper tackles the problem of quantizing implicit neural representations (INRs) by showing that non-uniform clustered quantization improves reconstruction performance at low bit-rates, achieving compression of NeRF to less than 16kb with minimal loss (323x smaller than original).
The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces poor performance at low-rates due to the network weight distributions changing over the course of training. In this work, we show that a non-uniform quantization of neural weights can lead to significant improvements. Specifically, we demonstrate that a clustered quantization enables improved reconstruction. Finally, by characterising a trade-off between quantization and network capacity, we demonstrate that it is possible (while memory inefficient) to reconstruct signals using binary neural networks. We demonstrate our findings experimentally on 2D image reconstruction and 3D radiance fields; and show that simple quantization methods and architecture search can achieve compression of NeRF to less than 16kb with minimal loss in performance (323x smaller than the original NeRF).