Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.23683 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908473942343680 |
|---|---|
| author | Chen, Jialei Xu, Wuhao He, Sipeng Huang, Baoru Ren, Dongchun |
| author_facet | Chen, Jialei Xu, Wuhao He, Sipeng Huang, Baoru Ren, Dongchun |
| contents | Vast and high-quality data are essential for end-to-end autonomous driving systems. However, current driving data is mainly collected by vehicles, which is expensive and inefficient. A potential solution lies in synthesizing data from real-world images. Recent advancements in 3D reconstruction demonstrate photorealistic novel view synthesis, highlighting the potential of generating driving data from images captured on the road. This paper introduces a novel method, I2V-GS, to transfer the Infrastructure view To the Vehicle view with Gaussian Splatting. Reconstruction from sparse infrastructure viewpoints and rendering under large view transformations is a challenging problem. We adopt the adaptive depth warp to generate dense training views. To further expand the range of views, we employ a cascade strategy to inpaint warped images, which also ensures inpainting content is consistent across views. To further ensure the reliability of the diffusion model, we utilize the cross-view information to perform a confidenceguided optimization. Moreover, we introduce RoadSight, a multi-modality, multi-view dataset from real scenarios in infrastructure views. To our knowledge, I2V-GS is the first framework to generate autonomous driving datasets with infrastructure-vehicle view transformation. Experimental results demonstrate that I2V-GS significantly improves synthesis quality under vehicle view, outperforming StreetGaussian in NTA-Iou, NTL-Iou, and FID by 45.7%, 34.2%, and 14.9%, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23683 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | I2V-GS: Infrastructure-to-Vehicle View Transformation with Gaussian Splatting for Autonomous Driving Data Generation Chen, Jialei Xu, Wuhao He, Sipeng Huang, Baoru Ren, Dongchun Computer Vision and Pattern Recognition Vast and high-quality data are essential for end-to-end autonomous driving systems. However, current driving data is mainly collected by vehicles, which is expensive and inefficient. A potential solution lies in synthesizing data from real-world images. Recent advancements in 3D reconstruction demonstrate photorealistic novel view synthesis, highlighting the potential of generating driving data from images captured on the road. This paper introduces a novel method, I2V-GS, to transfer the Infrastructure view To the Vehicle view with Gaussian Splatting. Reconstruction from sparse infrastructure viewpoints and rendering under large view transformations is a challenging problem. We adopt the adaptive depth warp to generate dense training views. To further expand the range of views, we employ a cascade strategy to inpaint warped images, which also ensures inpainting content is consistent across views. To further ensure the reliability of the diffusion model, we utilize the cross-view information to perform a confidenceguided optimization. Moreover, we introduce RoadSight, a multi-modality, multi-view dataset from real scenarios in infrastructure views. To our knowledge, I2V-GS is the first framework to generate autonomous driving datasets with infrastructure-vehicle view transformation. Experimental results demonstrate that I2V-GS significantly improves synthesis quality under vehicle view, outperforming StreetGaussian in NTA-Iou, NTL-Iou, and FID by 45.7%, 34.2%, and 14.9%, respectively. |
| title | I2V-GS: Infrastructure-to-Vehicle View Transformation with Gaussian Splatting for Autonomous Driving Data Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.23683 |