DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes
- URL: http://arxiv.org/abs/2409.04003v2
- Date: Mon, 25 Nov 2024 03:50:30 GMT
- Title: DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes
- Authors: Jianbiao Mei, Xuemeng Yang, Licheng Wen, Tao Hu, Yu Yang, Tiantian Wei, Yukai Ma, Min Dou, Botian Shi, Yong Liu,
- Abstract summary: We propose DreamForge, an advanced diffusion-based autoregressive video generation model tailored for 3D-controllable long-term generation.
To enhance the lane and foreground generation, we introduce perspective guidance and integrate object-wise position encoding.
We also propose motion-aware temporal attention to capture motion cues and appearance changes in videos.
- Score: 15.506076058742744
- License:
- Abstract: Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To alleviate these issues, we propose DreamForge, an advanced diffusion-based autoregressive video generation model tailored for 3D-controllable long-term generation. To enhance the lane and foreground generation, we introduce perspective guidance and integrate object-wise position encoding to incorporate local 3D correlation and improve foreground object modeling. We also propose motion-aware temporal attention to capture motion cues and appearance changes in videos. By leveraging motion frames and an autoregressive generation paradigm, we can autoregressively generate long videos (over 200 frames) using a 7-frame model, achieving superior quality compared to the baseline in 16-frame video evaluations. Finally, we integrate our method with the realistic simulation platform DriveArena to provide more reliable open-loop and closed-loop evaluations for vision-based driving agents. The project page is available at https://pjlab-adg.github.io/DriveArena/dreamforge.
Related papers
- VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models [71.9811050853964]
VideoJAM is a novel framework that instills an effective motion prior to video generators.
VideoJAM achieves state-of-the-art performance in motion coherence.
These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.
arXiv Detail & Related papers (2025-02-04T17:07:10Z) - Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model [83.31688383891871]
We propose a Spatial-Temporal simulAtion for drivinG (Stag-1) model to reconstruct real-world scenes.
Stag-1 constructs continuous 4D point cloud scenes using surround-view data from autonomous vehicles.
It decouples spatial-temporal relationships and produces coherent driving videos.
arXiv Detail & Related papers (2024-12-06T18:59:56Z) - InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models [75.03495065452955]
We present InfiniCube, a scalable method for generating dynamic 3D driving scenes with high fidelity and controllability.
Our method can generate controllable and realistic 3D driving scenes, and extensive experiments validate the effectiveness and superiority of our model.
arXiv Detail & Related papers (2024-12-05T07:32:20Z) - MyGo: Consistent and Controllable Multi-View Driving Video Generation with Camera Control [4.556249147612401]
MyGo is an end-to-end framework for driving video generation.
MyGo introduces motion of onboard cameras as conditions to make progress in camera controllability and multi-view consistency.
Results show that MyGo has achieved state-of-the-art results in both general camera-controlled video generation and multi-view driving video generation tasks.
arXiv Detail & Related papers (2024-09-10T03:39:08Z) - DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation [10.296670127024045]
DriveScape is an end-to-end framework for multi-view, 3D condition-guided video generation.
Our Bi-Directional Modulated Transformer (BiMot) ensures precise alignment of 3D structural information.
DriveScape excels in video generation performance, achieving state-of-the-art results on the nuScenes dataset with an FID score of 8.34 and an FVD score of 76.39.
arXiv Detail & Related papers (2024-09-09T09:43:17Z) - MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes [72.02827211293736]
We introduce MagicDrive3D, a novel pipeline for controllable 3D street scene generation.
Unlike previous methods that reconstruct before training the generative models, MagicDrive3D first trains a video generation model and then reconstructs from the generated data.
Our results demonstrate the framework's superior performance, showcasing its potential for autonomous driving simulation and beyond.
arXiv Detail & Related papers (2024-05-23T12:04:51Z) - Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video
Synthesis [69.83405335645305]
We argue that naively bringing advances of image models to the video generation domain reduces motion fidelity, visual quality and impairs scalability.
In this work, we build Snap Video, a video-first model that systematically addresses these challenges.
We show that a U-Net - a workhorse behind image generation - scales poorly when generating videos, requiring significant computational overhead.
This allows us to efficiently train a text-to-video model with billions of parameters for the first time, reach state-of-the-art results on a number of benchmarks, and generate videos with substantially higher quality, temporal consistency, and motion complexity.
arXiv Detail & Related papers (2024-02-22T18:55:08Z) - TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control.
A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects.
generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
arXiv Detail & Related papers (2023-12-01T15:24:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.