AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Generative Neural Fields by Mixtures of Neural Implicit Functions

Tackgeun You, Mijeong Kim, Jungtaek Kim, Bohyung Han

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 1 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 mNIF rather than FunctaCelebA-HQ 64² image reconstruction · CelebA-HQ 64²PSNR: 26.6 -> 34.5Improved
use mNIF (L) rather than DPFCelebA-HQ 64² image generation · CelebA-HQ 64²FID: 13.2 -> 13.2No clear effect
use mNIF rather than GEMShapeNet 64³ voxel generation · ShapeNet 64³coverage: 0.409 -> 0.437Improved
use mNIF rather than GEMShapeNet 64³ voxel reconstruction · ShapeNet 64³MSE: 0.0153 -> 0.0161Hurt
use mNIF rather than FunctaSRN Cars scene reconstruction · SRN CarsPSNR: 24.2 -> 25.9Improved
project layer-specific mixture coefficients from a latent vector instead of using layer-specific coefficients directly (ablation)mNIF on CelebA-HQ 64² · CelebA-HQ 64² testPSNR: 24.35 -> 25.09Improved
use layer-specific rather than shared coefficients across layers (ablation)mNIF on CelebA-HQ 64² · CelebA-HQ 64² testPSNR: 22.11 -> 24.35Improved
increase the number of mixture bases (ablation)mNIF on CelebA-HQ 64² · CelebA-HQ 64² testPSNR: 21.84 -> 25.09 -> 25.74 -> 25.85Improved
increase latent dimension H (ablation)mNIF on CelebA-HQ 64² · CelebA-HQ 64² testPSNR: 25.35 -> 27.92 -> 29.45Improved
include second-order gradients in meta-learning (ablation)mNIF context adaptation on CelebA-HQ 64² · CelebA-HQ 64²PSNR: 22.68 -> 26.64Improved
increase meta-learning inner steps from 3 to 5 (ablation)mNIF context adaptation on CelebA-HQ 64² · CelebA-HQ 64²PSNR: 26.64 -> 26.77Improved
extend context adaptation training from 800 to 1200 epochs (ablation)mNIF (L) on CelebA-HQ 64² · CelebA-HQ 64²FID: 14.30 -> 15.25Hurt

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