AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

Yuhwan Jeong, HYEONSEONG KIM, Daehyun We, Seonkyu Song, Jinnyeong Yang, Hyun-Kurl Jang, Youngho Yoon, KUK-JIN YOON

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 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
add object-presence ratio loss (upweight rare classes) (ablation)FrozenDrive · nuScenes val 3DOD ablation (UniAD)3DOD mAP: 16.1 -> 21.9Improved
add object-presence ratio loss (ablation)FrozenDrive · nuScenes val 3DOD ablation (UniAD)Motorcycle AP: 0.4 -> 10.0Improved
add temporal reference self-attention to MISA (ablation)FrozenDrive · nuScenes val toy ablation (BEV seg, FVD)FVD: 174.2 -> 144.1Improved
add multi-view inflated self-attention to TRSA (ablation)FrozenDrive · nuScenes val toy ablation (BEV seg, FVD)BEV seg Drivable mIoU: 51.9 -> 56.5Improved
augment normal-weather training data with FrozenDrive night imagesSparseDrive · nuScenes night augmentation (SparseDrive)3DOD mAP: 6.62 -> 18.15Improved
augment with FrozenDrive rain imagesSparseDrive · nuScenes rain augmentation (SparseDrive)planning L2 avg (m): 0.75 -> 0.58Improved
FrozenDrive rain augmentation versus DriveArena on NDSSparseDrive · nuScenes rain augmentation (SparseDrive)NDS: 45.25 -> 44.26Hurt
use frozen backbone with parameter-free attention instead of learnable cross-attention (SD + CA) (ablation)FrozenDrive · Lane alignment mIoUlane mIoU: 33.55 -> 33.58No clear effect
use frozen backbone for text alignment on unseen snow (ablation)FrozenDrive · CLIP score, snowCLIP score: 0.2277 -> 0.2507 (vs DriveArena)Improved
FrozenDrive vs MagicDrive-V2 on temporal consistencyFrozenDrive · VBench temporal consistencyVBench subject consistency: 0.7966 -> 0.7724Hurt
FrozenDrive vs video-diffusion baselines on FVDFrozenDrive · nuScenes val generation fidelity (UniAD)FVD: 81.6 -> 136.8 (MagicDrive-V2)Hurt

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