Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
Yuqing Wen, Yucheng Zhao, Yingfei Liu, Binyuan Huang, Fan Jia, Yanhui, Wang, Chi Zhang, Tiancai Wang, Xiaoyan Sun, Xiangyu Zhang

TL;DR
Panacea+ is a novel framework for generating high-quality, panoramic, and controllable driving scene videos that improve the training of autonomous driving models across multiple tasks.
Contribution
It introduces a multi-view appearance noise prior and super-resolution modules to enhance video consistency and resolution, advancing autonomous driving data generation.
Findings
Generated videos significantly improve 3D object tracking accuracy.
Enhanced video resolution benefits lane detection tasks.
Framework proves effective across multiple datasets and tasks.
Abstract
The field of autonomous driving increasingly demands high-quality annotated video training data. In this paper, we propose Panacea+, a powerful and universally applicable framework for generating video data in driving scenes. Built upon the foundation of our previous work, Panacea, Panacea+ adopts a multi-view appearance noise prior mechanism and a super-resolution module for enhanced consistency and increased resolution. Extensive experiments show that the generated video samples from Panacea+ greatly benefit a wide range of tasks on different datasets, including 3D object tracking, 3D object detection, and lane detection tasks on the nuScenes and Argoverse 2 dataset. These results strongly prove Panacea+ to be a valuable data generation framework for autonomous driving.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation · Computer Graphics and Visualization Techniques · Advanced Vision and Imaging
