Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention

• URL: http://arxiv.org/abs/2412.03520v2
• Date: Mon, 09 Dec 2024 06:58:05 GMT
• Title: Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention
• Authors: Hannan Lu, Xiaohe Wu, Shudong Wang, Xiameng Qin, Xinyu Zhang, Junyu Han, Wangmeng Zuo, Ji Tao,
• Abstract summary: We present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the dimensions. CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos.
• Score: 61.3281618482513
• License:
• Abstract: Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial, temporal, and view dimensions. However, these approaches often struggle to maintain consistency across dimensions, particularly when handling fast-moving objects that appear at different times and viewpoints. In this paper, we present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the spatial, temporal, and viewpoint dimensions. We also propose a lightweight controller tailored for CogDriving, i.e., Micro-Controller, which uses only 1.1% of the parameters of the standard ControlNet, enabling precise control over Bird's-Eye-View layouts. To enhance the generation of object instances crucial for autonomous driving, we propose a re-weighted learning objective, dynamically adjusting the learning weights for object instances during training. CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos. The project can be found at https://luhannan.github.io/CogDrivingPage/.

Related papers

• Physical Informed Driving World Model [47.04423342994622]
  DrivePhysica is an innovative model designed to generate realistic driving videos that adhere to essential physical principles. We achieve state-of-the-art performance in driving video generation quality (3.96 FID and 38.06 FVD on the Nuscenes dataset) and downstream perception tasks.
  arXiv  Detail & Related papers  (2024-12-11T14:29:35Z)
• 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)
• UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving [18.189392365510848]
  UniMLVG is a unified framework designed to generate extended street multi-perspective videos under precise control. By integrating single- and multi-view driving videos into the training data, our approach updates cross-frame and cross-view modules across three stages. Our framework achieves improvements of 21.4% in FID and 36.5% in FVD.
  arXiv  Detail & Related papers  (2024-12-06T08:27:53Z)
• 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)
• DiVE: DiT-based Video Generation with Enhanced Control [23.63288169762629]
  We propose first DiT-based framework specifically designed for generating temporally and multi-view consistent videos. Specifically, the proposed framework leverages a parameter-free spatial view-inflated attention mechanism to guarantee the cross-view consistency.
  arXiv  Detail & Related papers  (2024-09-03T04:29:59Z)
• Linking vision and motion for self-supervised object-centric perception [16.821130222597155]
  Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. We adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs.
  arXiv  Detail & Related papers  (2023-07-14T04:21:05Z)
• Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling [96.31941517446859]
  We propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only.
  arXiv  Detail & Related papers  (2023-01-03T08:52:49Z)
• MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views [60.538802124885414]
  We present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for multi-class object detection and drivable space segmentation. MVLidarNet is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input. We show results on both KITTI and a much larger internal dataset, thus demonstrating the method's ability to scale by an order of magnitude.
  arXiv  Detail & Related papers  (2020-06-09T21:28:17Z)

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.