AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Learnable Radial Basis Positional Embedding for Coordinate-MLPs

Sameera Ramasinghe, Simon Lucey

AAAI 2023 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use graph-Laplacian-trained, coordinate-specific super-Gaussian standard deviations instead of matched RFFCoordinate-MLPs · 1D signal encodingTest PSNR: 26.03 -> 31.17Improved
Use graph-Laplacian-trained, coordinate-specific super-Gaussian standard deviations instead of matched RFFNeRF-style coordinate-MLP · Realistic Synthetic 3D signal encodingPSNR: 31.13 -> 32.17Improved
Use graph-Laplacian-trained, coordinate-specific super-Gaussian standard deviations instead of matched RFFNeRF-style coordinate-MLP · Realistic Synthetic 3D signal encodingSSIM: 0.947 -> 0.981Improved
Train embedding parameters end-to-end with network weights instead of using the proposed procedure (ablation)Super-Gaussian coordinate-MLP · 1D signal encodingTest PSNR: 31.17 -> 21.44Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)Super-Gaussian coordinate-MLP · 1D signal encodingTest PSNR: 27.19 -> 31.17Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)NeRF-style coordinate-MLP · Realistic Synthetic 3D signal encodingPSNR: 25.41 -> 32.17Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)NeRF-style coordinate-MLP · Realistic Synthetic 3D signal encodingSSIM: 0.891 -> 0.981Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)Coordinate-MLP · 2D image encoding, 25% regular training datamean PSNR: 17.40 -> 19.99Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)Coordinate-MLP · 2D image encoding, 10% regular training datamean PSNR: 16.17 -> 18.68Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)Coordinate-MLP · 2D image encoding, 25% random training datamean PSNR: 16.80 -> 19.33Hurt
Use uniform standard deviations instead of graph-Laplacian-trained coordinate-specific values (ablation)Coordinate-MLP · 2D image encoding, 10% random training datamean PSNR: 14.91 -> 17.64Hurt
Use one signal's selected RFF parameters across signals rather than tuning per signal (ablation)RFF coordinate-MLP · 1D signal encodingTest PSNR: 26.03 -> 23.24Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy