AI Paper Atlas

Research map / Video / Video generation

MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

Ruiyuan Gao, Kai Chen, Bo Xiao, Lanqing Hong, Zhenguo Li, Qiang Xu

ICCV 2025 · Video › Video generation · approach: World-model video generation · 80 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
replace MagicDrive with MagicDrive-V2 (DiT, 3D VAE)MagicDrive · nuScenes video generation (first 16 frames, validation)FVD: 218.12 -> 94.84Improved
replace MagicDrive with MagicDrive-V2MagicDrive · nuScenes video generation (first 16 frames, validation)mAP: 11.86 -> 18.17Improved
replace MagicDrive image model with MagicDrive-V2MagicDrive (Img) · nuScenes image generation (validation)FID: 16.20 -> 20.91Hurt
replace MagicDrive image model with MagicDrive-V2MagicDrive (Img) · nuScenes image generation (validation)Vehicle mIoU: 27.01 -> 32.73Improved
add longer videos to low-resolution training (ablation)MagicDrive-V2 · Training data mixing ablation (nuScenes)mAP: 10.17 -> 10.51No clear effect
add higher-resolution videos to training (ablation)MagicDrive-V2 · Training data mixing ablation (nuScenes)mAP: 10.17 -> 14.91Improved
add mixed frame lengths on top of mixed resolutions (ablation)MagicDrive-V2 · Training data mixing ablation (nuScenes)FVD: 96.34 -> 99.66Hurt
add mixed frame lengths on top of mixed resolutions (ablation)MagicDrive-V2 · Training data mixing ablation (nuScenes)mAP: 14.91 -> 15.44Improved
use spatial-temporal 4x downsampling control encoder instead of global temporal reduction (ablation)MagicDrive-V2 · over-fitting validation lossvalidation lossImproved
add MVDiT cross-view block (ablation)MagicDrive-V2 · multi-view consistencyvisual consistencyImproved
use CogVAE instead of SD VAE (2D)video VAE · VAE reconstruction PSNR, 848x1600 17 framesPSNR: 33.2846 -> 36.0011Improved
use CogVAE instead of Open-Sora VAEvideo VAE · VAE reconstruction PSNR, 424x800 17 framesPSNR: 30.2779 -> 33.5852Improved

Later papers that compared with this method

6 later accepted papers report MagicDrive-V2 as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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