Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.13558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917129954000896 |
|---|---|
| author | Yang, Yu Liang, Alan Mei, Jianbiao Ma, Yukai Liu, Yong Lee, Gim Hee |
| author_facet | Yang, Yu Liang, Alan Mei, Jianbiao Ma, Yukai Liu, Yong Lee, Gim Hee |
| contents | Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporally consistent generation. However, large-scale 3D scene generation requiring spatial coherence remains underexplored. In this paper, we present X-Scene, a novel framework for large-scale driving scene generation that achieves geometric intricacy, appearance fidelity, and flexible controllability. Specifically, X-Scene supports multi-granular control, including low-level layout conditioning driven by user input or text for detailed scene composition, and high-level semantic guidance informed by user intent and LLM-enriched prompts for efficient customization. To enhance geometric and visual fidelity, we introduce a unified pipeline that sequentially generates 3D semantic occupancy and corresponding multi-view images and videos, ensuring alignment and temporal consistency across modalities. We further extend local regions into large-scale scenes via consistency-aware outpainting, which extrapolates occupancy and images from previously generated areas to maintain spatial and visual coherence. The resulting scenes are lifted into high-quality 3DGS representations, supporting diverse applications such as simulation and scene exploration. Extensive experiments demonstrate that X-Scene substantially advances controllability and fidelity in large-scale scene generation, empowering data generation and simulation for autonomous driving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability Yang, Yu Liang, Alan Mei, Jianbiao Ma, Yukai Liu, Yong Lee, Gim Hee Computer Vision and Pattern Recognition Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporally consistent generation. However, large-scale 3D scene generation requiring spatial coherence remains underexplored. In this paper, we present X-Scene, a novel framework for large-scale driving scene generation that achieves geometric intricacy, appearance fidelity, and flexible controllability. Specifically, X-Scene supports multi-granular control, including low-level layout conditioning driven by user input or text for detailed scene composition, and high-level semantic guidance informed by user intent and LLM-enriched prompts for efficient customization. To enhance geometric and visual fidelity, we introduce a unified pipeline that sequentially generates 3D semantic occupancy and corresponding multi-view images and videos, ensuring alignment and temporal consistency across modalities. We further extend local regions into large-scale scenes via consistency-aware outpainting, which extrapolates occupancy and images from previously generated areas to maintain spatial and visual coherence. The resulting scenes are lifted into high-quality 3DGS representations, supporting diverse applications such as simulation and scene exploration. Extensive experiments demonstrate that X-Scene substantially advances controllability and fidelity in large-scale scene generation, empowering data generation and simulation for autonomous driving. |
| title | X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.13558 |