Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. (arXiv:2201.05989v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2201.05989

Neural graphics primitives, parameterized by fully connected neural networks,
can be costly to train and evaluate. We reduce this cost with a versatile new
input encoding that permits the use of a smaller network without sacrificing
quality, thus significantly reducing the number of floating point and memory
access operations: a small neural network is augmented by a multiresolution
hash table of trainable feature vectors whose values are optimized through
stochastic gradient descent. The multiresolution structure allows the network
to disambiguate …

arxiv cv graphics neural