AI Paper Atlas

Research map / 3D vision / Face and shape

COSMO-INR: Complex Sinusoidal Modulation for Implicit Neural Representations

Pandula Thennakoon, Avishka Ranasinghe, Mario De Silva, Buwaneka Epakanda, Roshan Godaliyadda, Mervyn Parakrama Bandara Ekanayake, Vijitha R. Herath

ICLR 2026 · 3D vision › Face and shape · approach: Implicit neural representation design

Read the paper

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 complex sinusoidal modulation to the raised cosine activation (ablation)Raised cosine INR activation · INR image representationPSNRImproved
replace INCODE with COSMO-RC activationINR MLP · Kodak image representation (24 images)PSNR (dB): 35.57 -> 41.24Improved
replace INCODE with COSMO-RC activationINR MLP · NeRF Lego test setPSNR (dB): 26.05 -> 29.50Improved
replace INCODE with COSMO-RC activationINR MLP · DIV2K denoisingPSNR (dB): +0.46 dBImproved
replace baselines with COSMO-RC activationINR MLP · Celtic knots inpainting and Lucy occupancy volumePSNR / IoUImproved
replace baselines with COSMO-RC activationINR MLP · DIV2K super-resolution 2x, 4x, 6xPSNR (dB): FINER 32.94 -> 34.03 at 2x; INCODE 29.96 -> 30.42 at 4x; SIREN 27.31 -> 27.66 at 6xImproved
increase network width from 64 to 512 at depth 4 (ablation)COSMO-RC · Kodak image 22 representationPSNR (dB): 29.47 -> 52.00Improved
increase depth from 2 to 4 hidden layers at width 256 (ablation)COSMO-RC · Kodak image 22 representationPSNR (dB): 38.09 -> 39.57 -> 37.19Mixed
add prior embedder with sigmoid regularizer for activation parametersCOSMO-RC · all image tasksconvergence speedImproved
use COSMO-RC instead of SIREN, FINER, INCODE or WIREINR MLP · Kodak image 20 compute costtrain time (s/it): 0.435 -> 3.500 vs INCODEHurt

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