DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation

• URL: http://arxiv.org/abs/2409.05463v4
• Date: Thu, 12 Sep 2024 12:32:21 GMT
• Title: DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
• Authors: Wei Wu, Xi Guo, Weixuan Tang, Tingxuan Huang, Chiyu Wang, Dongyue Chen, Chenjing Ding,
• Abstract summary: 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.
• Score: 10.296670127024045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model. We propose DriveScape, an end-to-end framework for multi-view, 3D condition-guided video generation, capable of producing 1024 x 576 high-resolution videos at 10Hz. Unlike other methods limited to 2Hz due to the 3D box annotation frame rate, DriveScape overcomes this with its ability to operate under sparse conditions. Our Bi-Directional Modulated Transformer (BiMot) ensures precise alignment of 3D structural information, maintaining spatial-temporal consistency. 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. Our project homepage: https://metadrivescape.github.io/papers_project/drivescapev1/index.html

Related papers

• MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control [68.74166535159311]
  We introduce MagicDriveDiT, a novel approach based on the DiT architecture. By incorporating spatial-temporal conditional encoding, MagicDriveDiT achieves precise control over spatial-temporal latents. Experiments show its superior performance in generating realistic street scene videos with higher resolution and more frames.
  arXiv  Detail & Related papers  (2024-11-21T03:13:30Z)
• DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes [15.506076058742744]
  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.
  arXiv  Detail & Related papers  (2024-09-06T03:09:58Z)
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations [120.52120919834988]
  xGen-SynVideo-1 is a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens. DiT model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios.
  arXiv  Detail & Related papers  (2024-08-22T17:55:22Z)
• 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)
• Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation [35.52770785430601]
  We propose a novel hybrid video autoencoder, called HVtemporalDM, which can capture intricate dependencies more effectively. The HVDM is trained by a hybrid video autoencoder which extracts a disentangled representation of the video. Our hybrid autoencoder provide a more comprehensive video latent enriching the generated videos with fine structures and details.
  arXiv  Detail & Related papers  (2024-02-21T11:46:16Z)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)
• PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking [90.29143475328506]
  We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. We animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos.
  arXiv  Detail & Related papers  (2023-07-27T17:58:11Z)
• PV3D: A 3D Generative Model for Portrait Video Generation [94.96025739097922]
  We propose PV3D, the first generative framework that can synthesize multi-view consistent portrait videos. PV3D is able to support many downstream applications such as animating static portraits and view-consistent video motion editing.
  arXiv  Detail & Related papers  (2022-12-13T05:42:44Z)
• Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition [24.220358793070965]
  We introduce a new module to improve the capability of 3D convolution (emphLS3D-Conv) We add learnable 2D offsets to 3D convolution which aims to sample locations on spatial feature maps across frames. The experiments on video, video super-resolution, video denoising, and action recognition demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-22T09:20:49Z)

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.