Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
Preprint
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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- DriveDreamer: Towards Real-World-Drive World Models for Autonomous Driving2024
- WoVoGen: World Volume-Aware Diffusion for Controllable Multi-camera Driving Scene Generation2024
- Exploiting Diffusion Prior for Real-World Image Super-ResolutionInternational Journal of Computer Vision, 2024
- LAMP: Learn A Motion Pattern for Few-Shot Video Generation2024
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation2024
- Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection2023
- Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models2023
- Viewpoint Equivariance for Multi-View 3D Object Detection2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Cross-view Transformers for real-time Map-view Semantic Segmentation2022