Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.20471 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918131922894848 |
|---|---|
| author | Li, Jiusi Jiang, Jackson Miao, Jinyu Long, Miao Wen, Tuopu Jia, Peijin Liu, Shengxiang Yu, Chunlei Liu, Maolin Cai, Yuzhan Jiang, Kun Yang, Mengmeng Yang, Diange |
| author_facet | Li, Jiusi Jiang, Jackson Miao, Jinyu Long, Miao Wen, Tuopu Jia, Peijin Liu, Shengxiang Yu, Chunlei Liu, Maolin Cai, Yuzhan Jiang, Kun Yang, Mengmeng Yang, Diange |
| contents | Corner cases are crucial for training and validating autonomous driving systems, yet collecting them from the real world is often costly and hazardous. Editing objects within captured sensor data offers an effective alternative for generating diverse scenarios, commonly achieved through 3D Gaussian Splatting or image generative models. However, these approaches often suffer from limited visual fidelity or imprecise pose control. To address these issues, we propose G^2Editor, a framework designed for photorealistic and precise object editing in driving videos. Our method leverages a 3D Gaussian representation of the edited object as a dense prior, injected into the denoising process to ensure accurate pose control and spatial consistency. A scene-level 3D bounding box layout is employed to reconstruct occluded areas of non-target objects. Furthermore, to guide the appearance details of the edited object, we incorporate hierarchical fine-grained features as additional conditions during generation. Experiments on the Waymo Open Dataset demonstrate that G^2Editor effectively supports object repositioning, insertion, and deletion within a unified framework, outperforming existing methods in both pose controllability and visual quality, while also benefiting downstream data-driven tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation Li, Jiusi Jiang, Jackson Miao, Jinyu Long, Miao Wen, Tuopu Jia, Peijin Liu, Shengxiang Yu, Chunlei Liu, Maolin Cai, Yuzhan Jiang, Kun Yang, Mengmeng Yang, Diange Computer Vision and Pattern Recognition Corner cases are crucial for training and validating autonomous driving systems, yet collecting them from the real world is often costly and hazardous. Editing objects within captured sensor data offers an effective alternative for generating diverse scenarios, commonly achieved through 3D Gaussian Splatting or image generative models. However, these approaches often suffer from limited visual fidelity or imprecise pose control. To address these issues, we propose G^2Editor, a framework designed for photorealistic and precise object editing in driving videos. Our method leverages a 3D Gaussian representation of the edited object as a dense prior, injected into the denoising process to ensure accurate pose control and spatial consistency. A scene-level 3D bounding box layout is employed to reconstruct occluded areas of non-target objects. Furthermore, to guide the appearance details of the edited object, we incorporate hierarchical fine-grained features as additional conditions during generation. Experiments on the Waymo Open Dataset demonstrate that G^2Editor effectively supports object repositioning, insertion, and deletion within a unified framework, outperforming existing methods in both pose controllability and visual quality, while also benefiting downstream data-driven tasks. |
| title | Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.20471 |