AI Paper Atlas

Research map / Video / Video generation

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows

Janne Perini, Rafael Bischof, Moab Arar, Ayça Duran, Michael Kraus, Siddhartha Mishra, Bernd Bickel

ECCV 2026 · Video › Video generation · approach: World-model video generation · 2 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
full fine-tuning of DiT instead of LoRA (rank 512) (ablation)WinDiNet · Urban wind test setVRMSE: 0.746 -> 0.702Improved
scalar embedding conditioning instead of text prompts (ablation)WinDiNet · Urban wind test setVRMSE: 0.702 -> 0.616Improved
add color adapter around frozen VAE (ablation)WinDiNet · Urban wind test setVRMSE: 0.616 -> 0.577Improved
fine-tune VAE decoder (ablation)WinDiNet · Urban wind test setVRMSE: 0.616 -> 0.531Improved
add physics-informed losses to decoder fine-tuning (ablation)WinDiNet · Urban wind test setVRMSE: 0.531 -> 0.520Improved
fine-tune VAE decoder (ablation)VAE reconstruction · VAE reconstruction (test set)VRMSE: 0.188 -> 0.084Improved
add color adapter (ablation)VAE reconstruction · VAE reconstruction (test set)W1: 0.0157 -> 0.0167Hurt
add physics-informed losses to decoder fine-tuning (ablation)VAE reconstruction · VAE reconstruction (test set)VRMSE: 0.084 -> 0.070Improved
train DiT from scratch on fine-tuned VAE (remove video pretraining) (ablation)WinDiNet Dec. FT Physics · Urban wind test setVRMSE: 0.52 -> 0.57Hurt
train both DiT and VAE from scratch (ablation)WinDiNet Dec. FT Physics · Urban wind test setVRMSE: 0.52 -> 0.92Hurt
use higher classifier-free guidance scale (above 1.0) (ablation)WinDiNet · validation set grid searchVRMSENo clear effect
use WinDiNet instead of OFormer as optimization surrogatelayout optimizer · Single-inlet inverse optimization (GT CFD)discomfort fraction >5 m/s: 36.63% -> 12.80%Improved

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