AI Paper Atlas

Research map / Video / Video generation

GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation

Zhenya Yang, Zhe Liu, Yuxiang Lu, Liping Hou, Chenxuan Miao, Siyi Peng, Bailan Feng, Xiang Bai, Hengshuang Zhao

CVPR 2026 · Video › Video generation · approach: World-model video generation · 9 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 Mutual Control Attention (ablation)GenieDrive occupancy world model · nuScenes occupancy forecastingAvg. mIoU (%): 38.96 -> 42.59Improved
add end-to-end training of VAE and predictor (ablation)GenieDrive occupancy world model · nuScenes occupancy forecastingAvg. mIoU (%): 39.79 -> 42.59Improved
add continuous representation (vs vector quantization) (ablation)GenieDrive occupancy world model · nuScenes occupancy forecastingAvg. mIoU (%): 39.09 -> 42.59Improved
add continuous representation and E2E training together (ablation)GenieDrive occupancy world model · nuScenes occupancy forecastingAvg. mIoU (%): 35.24 -> 42.59Improved
apply end-to-end training to DOME (ablation)DOME · nuScenes occupancy forecastingAvg. mIoU (%): 27.10 -> 0.43Hurt
apply end-to-end training to I2-World (ablation)I2-World · nuScenes occupancy forecastingAvg. mIoU (%): 39.73 -> 10.09Hurt
add Normalized Multi-View Attention (ablation)GenieDrive video generator · nuScenes multi-view video (37 frames)FVD: 120.16 -> 98.06Improved
add cross normalization to multi-view attention (ablation)GenieDrive video generator · nuScenes multi-view video (37 frames)FVD: 212.67 -> 98.06Improved
add cross normalization to multi-view attention (ablation)GenieDrive video generator · nuScenes multi-view video (37 frames)mAP (%): 10.04 -> 19.84Improved
longer E2E training epochs (0 -> 4 epochs) (ablation)GenieDrive occupancy world model · nuScenes forecasting vs reconstructionreconstruction mIoU / forecasting mIoU: 86.15 -> 73.89 reconstruction mIoU; 39.79 -> 41.64 forecasting mIoUMixed
tri-plane GenieDrive vs I2-WorldGenieDrive occupancy world model · nuScenes occupancy forecastingAvg. mIoU (%): 39.73 -> 42.59Improved
tri-plane VAE vs I2-World on reconstruction IoUGenieDrive occupancy world model · nuScenes occupancy forecastingReconstruction IoU (%): 77.25 -> 75.53Hurt

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