Research map / Video / Video generation
ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask
Zhuoran Yang, Yanyong Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add instance identity mask in instance-masked attention (ablation) | ConsisDrive · nuScenes val (T+I)2V | NDS: 37.55 -> 41.38 | Improved |
| add instance identity mask in instance-masked attention (ablation) | ConsisDrive · nuScenes val (T+I)2V | IDS: 735 -> 525 | Improved |
| add instance identity mask in instance-masked attention (ablation) | ConsisDrive · nuScenes val (T+I)2V | FID: 5.29 -> 3.88 | Improved |
| add instance trajectory mask in instance-masked attention (ablation) | ConsisDrive · nuScenes val (T+I)2V | IDS: 1074 -> 525 | Improved |
| add instance trajectory mask in instance-masked attention (ablation) | ConsisDrive · nuScenes val (T+I)2V | FVD: 53.66 -> 37.23 | Improved |
| add instance-masked loss supervision (ablation) | ConsisDrive · nuScenes val (T+I)2V | NDS: 36.85 -> 41.38 | Improved |
| add instance-masked loss supervision (ablation) | ConsisDrive · nuScenes val (T+I)2V | FVD: 40.19 -> 37.23 | Improved |
| augment real data with ConsisDrive generated videos for training | StreamPETR · nuScenes val perception | NDS: 46.9 -> 54.6 | Improved |
| augment real data with ConsisDrive generated videos for training | StreamPETR · nuScenes val MOT | IDS: 687 -> 525 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Panacea — Panacea: Panoramic and Controllable Video Generation for Autonomous Driving (CVPR 2024) · better on 6 of 6 shared results
- MagicDrive-V2 — MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control (ICCV 2025) · better on 3 of 3 shared results
- InstaDrive — InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation (ICCV 2025) · better on 3 of 3 shared results
- DriveDreamer2 — DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025) · better on 2 of 2 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
- MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction (CVPR 2025 · similarity 0.90)
- Panacea: Panoramic and Controllable Video Generation for Autonomous Driving (CVPR 2024 · similarity 0.88)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.88)
- DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025 · similarity 0.88)
- DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion (CVPR 2025 · similarity 0.88)
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency (NeurIPS 2025 · similarity 0.87)
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.
