AI Paper Atlas

Research map / Video / Video generation

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Kai Zeng, Zhanqian Wu, Kaixin Xiong, Xiaobao Wei, Xiangyu Guo, Zhenxin Zhu, Kalok Ho, Lijun Zhou, Bohan Zeng, Ming Lu, Haiyang Sun, BING WANG and 3 more

ICLR 2026 · Video › Video generation · approach: World-model video generation

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
train on real plus synthetic data from earlier driving world models at equal epochs rather than pretrain then finetuneprior world-model augmentation · nuScenes detection 2x epochsmAP: 38.4 (real) vs 38.1 (SubjectDrive)No clear effect
add 420 Dream4Drive synthetic samples (<2%) to real dataperception detector · nuScenes detection 256x512, 1x epochsmAP: 34.5 -> 36.1Improved
add Dream4Drive synthetic data at equal 2x epochsperception detector · nuScenes detection 256x512, 2x epochsNDS: 50.4 -> 50.6Improved
add Dream4Drive synthetic data at 512x768perception detector · nuScenes detection 512x768, 1x epochsmAP: 36.1 -> 40.7Improved
use generative 3D-aware rendering instead of naive projection of 3D assets (ablation)Dream4Drive · nuScenes detection 512x768, 3x epochsmAP: 43.1 -> 44.5Improved
use generative rendering instead of naive insertion (ablation)Dream4Drive · nuScenes detection 512x768, 2x epochsmAOE: 37.5 -> 39.4Hurt
insert assets on left side rather than right side (ablation)Dream4Drive · nuScenes detection 512x768, 1x epochsmAOE: 51.4 -> 45.7Improved
insert assets at far distance instead of close (ablation)Dream4Drive · nuScenes detection 512x768, 1x epochsmAP: 39.7 -> 40.5Improved
use multi-view generated DriveObj3D assets instead of Trellis assets (ablation)Dream4Drive · nuScenes detection 512x768, 1x epochsmAP: 39.8 -> 40.7Improved
use multi-view assets instead of single-view Hunyuan3D assets (ablation)Dream4Drive · nuScenes detection 512x768, 1x epochsmAP: 40.2 -> 40.7Improved
increase OOD scenes from 7 to 35 (ablation)Dream4Drive · nuScenes detection 512x768, 1x epochsmAP: 40.7 -> 39.7Hurt
add style-transferred (rain, night) synthetic data (ablation)Dream4Drive · nuScenes detection 512x768, 2x epochsmAP: 43.6 -> 44.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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