AI Paper Atlas

Research map / 3D vision / Face and shape

SASNet: Spatially-Adaptive Sinusoidal Networks for INRs

Haoan Feng, Diana Aldana, Tiago Novello, Leila De Floriani

CVPR 2026 · 3D vision › Face and shape · approach: Implicit neural representation design · 2 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 SASNet instead of FINERSIREN-style INR · KodakPSNR: 37.72 -> 40.43Improved
use SASNet instead of FINERSIREN-style INR · KodakPSNR_edge: 34.67 -> 38.12Improved
add spatially-adaptive masks over SIREN fixed frequency embedding (ablation)SASNet · SDF reconstruction (Armadillo)error mapImproved
add spatially-adaptive masks to frequency embedding layer (ablation)SASNet · image fittingbackground noiseImproved
use SASNet instead of SIRENSIREN · CT medical imagesPSNR: 47.07 -> 50.21Improved
use SASNet instead of FINERFINER · CT medical imagesPSNR_edge: 45.56 -> 49.58Improved
use SASNet instead of FINERFINER · FFHQPSNR: 38.16 -> 39.69Improved
use SASNet instead of FINERFINER · FFHQnoisiness: 4.975 -> 4.278Improved
use SASNet instead of SIRENSIREN · 2D image fittingaverage step time (us): 29,224 -> 43,107Hurt
use SASNet instead of SIRENSIREN · 3D shape fittingaverage step time: 17,557 -> 22,175Hurt
use SASNet instead of SIRENSIREN · 2D image fittingtime to same training loss (minutes): 58 -> 10Improved
vary omega_0 for SASNet (ablation)SASNet · image fittingPSNRNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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