AI Paper Atlas

Research map / Image generation / Editing and style transfer

Physics-Informed Guided Disentanglement in Generative Networks

Fabio Pizzati, Pietro Cerri, Raoul de Charette

TPAMI 2023 · Image generation › Editing and style transfer · approach: Image-to-image translation · 17 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 differentiable-only parameter estimation instead of full genetic estimation of non-differentiable parameters (ablation)model-guided disentanglement · clear->rain (drop, nuScenes)Inception Score: 1.25 -> 1.53Improved
add physics-model guided disentanglement to MUNIT backboneMUNIT · clear->rain (drop, nuScenes)Inception Score: 1.21 -> 1.53Improved
add physics-model guided disentanglement to MUNIT backboneMUNIT · gray->color (dirt, WoodScape)LPIPS diversity: 0.656 -> 0.590Hurt
add physics-model guided disentanglement to MUNIT backboneMUNIT · synth->WCS fogInception Score: 1.22 -> 1.33Improved
add physics-model guided disentanglement to MUNIT backboneMUNIT · clear->snow composite watermark (Synthia)Inception Score: 1.17 -> 1.19Improved
finetune PSPNet on model-guided synthetic rain instead of Halder et al. rain renderingPSPNet · Semantic segmentation on rainy Cityscapes (25 images)AP: 25.6 -> 27.7Improved
finetune PSPNet on model-guided synthetic rain instead of original clear-image trainingPSPNet · Semantic segmentation on rainy Cityscapes (25 images)AP: 18.7 -> 27.7Improved
use neural guidance (DirtyGAN) instead of physical dirt modelgray->color dirt · gray->color (dirt, WoodScape)SSIM and PSNRHurt
use neural guidance (DirtyGAN) instead of physical dirt modelgray->color dirt · gray->color (dirt, WoodScape)quality and diversityImproved
add refraction, shape and thickness variability to simple raindrop model (complex model vs Refract/Gaussian) (ablation)raindrop guidance model · clear->rain (drop, nuScenes)GAN metricsImproved
use correct raindrop model instead of wrong model (watermark, dirt, fence) (ablation)RobotCar raindrop guidance · RobotCar raindropFID: 329.17 -> 135.32Improved
add Disentanglement Guidance with threshold gamma=0.75 (vs 0 or 1) (ablation)model-guided GAN · clear->rain (drop, nuScenes)qualitative disentanglement: gamma 0 -> 0.75Improved

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