AI Paper Atlas

Research map / 3D vision / Face and shape

Implicit Neural Representation with Multi-Scale Sine Activation

Jufeng Han, Shu Wei, Min Wu, Lina Yu, Weijun Li, Linjun Sun, Hong Qin, Yan Pang

AAAI 2026 · 3D vision › Face and shape · approach: Implicit neural representation design · 3 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
add amplitude modulation (F^-1 scaling) (ablation)MSA · PDE: Poisson (modified source term)relative l2 error: 1.31×101 -> 3.49 × 10−5Improved
add amplitude modulation (F^-1 scaling) (ablation)MSA · PDE: Poisson (modified source term)mean-log gradient layer1: 29.01 -> -3.47Improved
use logarithmic instead of linear frequency spacing (ablation)MSA-PINN · 2D Helmholtzrelative l2 errorImproved
use logarithmic instead of uniform random frequency sampling (ablation)MSA-PINN · 2D Helmholtzrelative l2 errorImproved
use MSA activation instead of SIREN/WIRE/FINER/STAFMLP INR · 1D multi-scale function fittingMSE: above 1 × 10−8 -> 7.96×10−14Improved
use MSA instead of SIRENMLP INR · BigBuckBunny video (100 frames)PSNR (dB): 40.19 -> 42.74Improved
use MSA instead of SIRENMLP INR · 3D shape SDF: DragonIoU: 0.9878 -> 0.9901Improved
use MSA-PINN instead of PINNPINN · PDE Heatrelative l2 error: 1.00e+00 -> 1.93e-04Improved
use MSA-PINN instead of sf-PINNPINN · PDE Advectionrelative l2 error: 9.93e-01 -> 3.35e-04Improved
use MSA-PINN instead of GP-HM-StMPINN · PDE Poissonrelative l2 error: 1.26e-04 -> 1.03e-04Improved
use MSA instead of SIREN (training cost)MLP INR · BigBuckBunny videotraining time (min): 165.39 -> 166.46Hurt
use MSA instead of ReLU (NTK spectrum)MLP INR · 1D function fittingNTK eigenvalue ratio r_remain: ReLU r1 above 60% -> MSA r_remain over 60%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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