InfinityDrive: Breaking Time Limits in Driving World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915047424393216 |
|---|---|
| author | Guo, Xi Ding, Chenjing Dou, Haoxuan Zhang, Xin Tang, Weixuan Wu, Wei |
| author_facet | Guo, Xi Ding, Chenjing Dou, Haoxuan Zhang, Xin Tang, Weixuan Wu, Wei |
| contents | Autonomous driving systems struggle with complex scenarios due to limited access to diverse, extensive, and out-of-distribution driving data which are critical for safe navigation. World models offer a promising solution to this challenge; however, current driving world models are constrained by short time windows and limited scenario diversity. To bridge this gap, we introduce InfinityDrive, the first driving world model with exceptional generalization capabilities, delivering state-of-the-art performance in high fidelity, consistency, and diversity with minute-scale video generation. InfinityDrive introduces an efficient spatio-temporal co-modeling module paired with an extended temporal training strategy, enabling high-resolution (576$\times$1024) video generation with consistent spatial and temporal coherence. By incorporating memory injection and retention mechanisms alongside an adaptive memory curve loss to minimize cumulative errors, achieving consistent video generation lasting over 1500 frames (more than 2 minutes). Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving. Our project homepage: https://metadrivescape.github.io/papers_project/InfinityDrive/page.html |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01522 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InfinityDrive: Breaking Time Limits in Driving World Models Guo, Xi Ding, Chenjing Dou, Haoxuan Zhang, Xin Tang, Weixuan Wu, Wei Computer Vision and Pattern Recognition Autonomous driving systems struggle with complex scenarios due to limited access to diverse, extensive, and out-of-distribution driving data which are critical for safe navigation. World models offer a promising solution to this challenge; however, current driving world models are constrained by short time windows and limited scenario diversity. To bridge this gap, we introduce InfinityDrive, the first driving world model with exceptional generalization capabilities, delivering state-of-the-art performance in high fidelity, consistency, and diversity with minute-scale video generation. InfinityDrive introduces an efficient spatio-temporal co-modeling module paired with an extended temporal training strategy, enabling high-resolution (576$\times$1024) video generation with consistent spatial and temporal coherence. By incorporating memory injection and retention mechanisms alongside an adaptive memory curve loss to minimize cumulative errors, achieving consistent video generation lasting over 1500 frames (more than 2 minutes). Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving. Our project homepage: https://metadrivescape.github.io/papers_project/InfinityDrive/page.html |
| title | InfinityDrive: Breaking Time Limits in Driving World Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.01522 |