Papers of the day   All papers

Overfit Neural Networks as a Compact Shape Representation

Comments

Alec Jacobson: Purposefully overfit neural networks are an efficient surface representation for solid 3D shapes In https://arxiv.org/abs/2009.09808 with Thomas Davies, @DerekRenderling, we make a few observations: https://t.co/ai9il42tRy

22 replies, 981 likes


Sam Finlayson: Clever....

1 replies, 36 likes


David Farrell: This looks like a really promising way of representing 3D surfaces!

0 replies, 19 likes


Adrien Gaidon: This field is crazy. In the best possible way 😁 Amazing progress at a breakneck speed.

0 replies, 11 likes


Beast: Using Neural Nets directly as compression, brilliant!

0 replies, 1 likes


Jakub Valtar: Compression through overfitting neural networks, amazing results

0 replies, 1 likes


Content

Found on Sep 22 2020 at https://arxiv.org/pdf/2009.09808.pdf

PDF content of a computer science paper: Overfit Neural Networks as a Compact Shape Representation