AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Controlling generative models with continuous factors of variations

Antoine Plumerault, Hervé Le Borgne, Céline Hudelot

ICLR 2020 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 75 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 the Gaussian frequency-weighted reconstruction loss instead of MSEGenerative-model inversion · ILSVRC, 1000 categoriesmean LPIPS: 0.57 -> 0.52Improved
Use the Gaussian frequency-weighted reconstruction loss instead of DSSIMGenerative-model inversion · ILSVRC, 1000 categoriesmean LPIPS: 0.58 -> 0.52Improved
Use the Gaussian frequency-weighted reconstruction loss instead of MSEGenerative-model inversion · ILSVRC, 1000 categoriesstd LPIPS: 0.14 -> 0.12Improved
Use the Gaussian frequency-weighted reconstruction loss instead of DSSIMGenerative-model inversion · ILSVRC, 1000 categoriesstd LPIPS: 0.12 -> 0.12No clear effect
Increase β in the β-VAE (ablation)β-VAE on dSprites · dSprites, object positionstandard deviation of measured position over control parameter tImproved
Constrain the optimized latent code to a ball of radius √d (ablation)Generative-model inversion · ILSVRC reconstructionsreconstruction artifactsImproved
Estimate transformed latent codes through sequential small transformations, initializing each step from the previous resultLatent-space trajectory estimation · Image transformationsoptimization convergenceImproved
Learn a shared direction from merged category trajectoriesBigGAN · ILSVRC validation categories, position and scalecontrol of transformationImproved

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