Variable Bitrate Neural Fields. (arXiv:2206.07707v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07707

Neural approximations of scalar and vector fields, such as signed distance
functions and radiance fields, have emerged as accurate, high-quality
representations. State-of-the-art results are obtained by conditioning a neural
approximation with a lookup from trainable feature grids that take on part of
the learning task and allow for smaller, more efficient neural networks.
Unfortunately, these feature grids usually come at the cost of significantly
increased memory consumption compared to stand-alone neural network models. We
present a dictionary method for compressing …

arxiv cv neural