CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving

• URL: http://arxiv.org/abs/2503.22231v2
• Date: Sat, 05 Apr 2025 15:43:06 GMT
• Title: CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving
• Authors: Yishen Ji, Ziyue Zhu, Zhenxin Zhu, Kaixin Xiong, Ming Lu, Zhiqi Li, Lijun Zhou, Haiyang Sun, Bing Wang, Tong Lu,
• Abstract summary: We introduce a novel spatial adaptive generation framework, CoGen, to achieve controllable multi-view videos with high 3D consistency.<n>By replacing coarse 2D conditions with fine-grained 3D representations, our approach significantly enhances the spatial consistency of the generated videos.<n>Results demonstrate that this method excels in preserving geometric fidelity and visual realism, offering a reliable video generation solution for autonomous driving.
• Score: 25.156989992025625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout conditions (e.g., HD maps and bounding boxes), can produce photorealistic driving videos, achieving controllable multi-view videos with high 3D consistency remains a major challenge. To tackle this, we introduce a novel spatial adaptive generation framework, CoGen, which leverages advances in 3D generation to improve performance in two key aspects: (i) To ensure 3D consistency, we first generate high-quality, controllable 3D conditions that capture the geometry of driving scenes. By replacing coarse 2D conditions with these fine-grained 3D representations, our approach significantly enhances the spatial consistency of the generated videos. (ii) Additionally, we introduce a consistency adapter module to strengthen the robustness of the model to multi-condition control. The results demonstrate that this method excels in preserving geometric fidelity and visual realism, offering a reliable video generation solution for autonomous driving.

Related papers

• I2V3D: Controllable image-to-video generation with 3D guidance [42.23117201457898]
  IV23D is a framework for animating static images into dynamic videos with precise 3D control.<n>Our approach combines the precision of a computer graphics pipeline with advanced generative models.
  arXiv  Detail & Related papers  (2025-03-12T18:26:34Z)
• TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
  TripoSG is a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images.<n>The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images.<n>To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
  arXiv  Detail & Related papers  (2025-02-10T16:07:54Z)
• 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.<n>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)
• 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)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior [97.694840981611]
  We propose a two-stage 2D-lifting framework, namely DreamControl. It generates fine-grained objects with control-based score distillation. DreamControl can generate high-quality 3D content in terms of both geometry consistency and texture fidelity.
  arXiv  Detail & Related papers  (2023-12-11T15:12:50Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)

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.