AI Paper Atlas

Research map / 3D vision / Face and shape

Streamable Neural Fields

Junwoo Cho, Seungtae Nam, Daniel Rho, Jong Hwan Ko, Eunbyung Park

ECCV 2022 · 3D vision › Face and shape · approach: Implicit neural representation design

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 progressive growing with weight reuse instead of slimmable training (ablation)streamable neural field · Kodak spectral growing, sub-network 4PSNR: 29.19 -> 30.91Improved
use progressive growing instead of slimmable training (ablation)streamable neural field · UVG temporal growing, sub-network 3PSNR: 34.54 -> 38.22Improved
use progressive growing instead of slimmable training (ablation)streamable neural field · Kodak spatial growing, sub-network 1PSNR: 24.49 -> 30.04Improved
train streamable progressive model instead of individual modelsstreamable neural field · Kodak spectral growing, sub-network 3PSNR: 29.78 -> 29.29Hurt
train streamable progressive model instead of individual modelsstreamable neural field · Kodak spectral growing, sub-network 3LPIPS: 0.246 -> 0.190Improved
train streamable progressive model instead of individual modelsstreamable neural field · Kodak spatial growing, sub-network 2PSNR: 28.82 -> 29.62Improved
train streamable progressive model instead of individual modelsstreamable neural field · UVG temporal growing, sub-network 3PSNR: 37.60 -> 38.22Improved
train streamable progressive model instead of individual modelsstreamable neural field · 3D spectral growing armadillo, sub-network 2Chamfer distance: 0.137 -> 0.032Improved
share parameters across sub-networks instead of separate modelsstreamable neural field · Kodak image 23 parameter countparameters: 590K -> 195KImproved
use proposed weight initialization instead of SIREN initialization for newly added weights (ablation)streamable neural field · Kodak (averaged PSNR curve)PSNRImproved
use proposed initialization instead of SIREN initialization (ablation)streamable neural field · activation and gradient statisticsactivation/gradient distributionNo clear effect
share parameters via progressive growingstreamable neural field · Kodak image 19 loss surfacetraining stabilityImproved

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