From 7b5d8fb47b71e64625839f27b5eeb1bc35c430ea Mon Sep 17 00:00:00 2001 From: Sylwester Klocek Date: Sun, 11 Feb 2024 14:45:39 -0800 Subject: [PATCH] Update README.md with first successful Neural Implicit Representation approach Hudos should be given to first successful implementation and paper. First it was created in 2018: https://scholar.google.ca/citations?view_op=view_citation&hl=en&user=eWZ79r8AAAAJ&citation_for_view=eWZ79r8AAAAJ:qjMakFHDy7sC And code: https://github.com/Zixxy/hyperpicture Then it was refined to paper I am inserting in readme update, that paper has motivated authors of "Implicit Neural Rerpresentations with Periodic Activation Functions" to explore discovered above phenomena. Authors have reused representation discovered above and activation functions. --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 5105190..f7bb245 100644 --- a/README.md +++ b/README.md @@ -75,8 +75,9 @@ imitation tasks. # Papers ## Implicit Neural Representations of Geometry -The following three papers first (and concurrently) demonstrated that implicit neural representations outperform grid-, point-, and mesh-based +The following four papers first (and concurrently) demonstrated that implicit neural representations outperform grid-, point-, and mesh-based representations in parameterizing geometry and seamlessly allow for learning priors over shapes. +* [Hypernetwork functional image representation](https://arxiv.org/pdf/1902.10404.pdf) (Klocek et al. 2019) * [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://arxiv.org/abs/1901.05103) (Park et al. 2019) * [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://arxiv.org/abs/1812.03828) (Mescheder et al. 2019) * [IM-Net: Learning Implicit Fields for Generative Shape Modeling](https://arxiv.org/abs/1812.02822) (Chen et al. 2018)