AI Paper Atlas

Research map / 3D vision / Face and shape

Closed-Form Implicit Neural Representations

Woojin Cho, Junghwan Park

NeurIPS 2026 · 3D vision › Face and shape · approach: Implicit neural representation design · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ELM-INR, a backpropagation-free implicit neural representation that decomposes the domain into overlapping subdomains and fits each with a closed-form Extreme Learning Machine.

Problem

Training implicit neural representations to capture fine-scale details relies on iterative backpropagation and suffers from spectral bias when target signals have highly non-uniform frequency content.

Approach

Replaces iterative gradient-based training with closed-form least-squares fitting of Extreme Learning Machines on overlapping spatial subdomains, so each local problem is solved directly rather than by backpropagation.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace backprop-trained INRs with closed-form local ELM + partition of unityELM-INR vs SIREN/FFN/GaussNet/WIRE · Kodak, WorldView-3, Sentinel-2, MRIPSNR (dB): kodim05 31.12 (SIREN) -> 79.03Improved
replace backprop-trained INRs with closed-form ELM-INRNavier-Stokes volume · Navier-Stokes (2+1)DMAE / time: MAE 4.22e-3 -> 5.68e-5; time 1,960 s -> 0.015 sImproved
add BEAM adaptive partitioning instead of regular mesh (same N) (ablation)ELM-INR, m=256 · kodim20PSNR (dB): 26.0 -> 27.5Improved
add BEAM adaptive partitioning instead of regular mesh (same N) (ablation)ELM-INR, m=512 · kodim20PSNR (dB): 29.6 -> 32.3Improved
add BEAM adaptive partitioning instead of regular mesh (same N) (ablation)ELM-INR, m=1024 · ERA5 winterMAE: 0.398 -> 0.363Improved
add BEAM adaptive partitioning instead of regular mesh (same N) (ablation)ELM-INR, m=2048 · ERA5 winterMAE: 0.317 -> 0.288Improved
increase hidden nodes m (ablation)ELM-INR · cameraman 512x512PSNRImproved
add Random Fourier Features encoding (ablation)ELM-INR · cameraman 512x512PSNR saturation vs mImproved
give baselines up to 10x CO2/compute budget (ablation)SIREN, FFN, GaussNet, WIRE · cameraman 256x256PSNR (dB): SIREN 20.2 -> 27.1 (still far below ELM-INR 77.8)Improved

Experimental setup

Builds on: Extreme Learning Machine implicit neural representations

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