Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.06109 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916844146786304 |
|---|---|
| author | Zhang, Jinhua Sheng, Hualian Cai, Sijia Deng, Bing Liang, Qiao Li, Wen Fu, Ying Ye, Jieping Gu, Shuhang |
| author_facet | Zhang, Jinhua Sheng, Hualian Cai, Sijia Deng, Bing Liang, Qiao Li, Wen Fu, Ying Ye, Jieping Gu, Shuhang |
| contents | Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the innovative integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a novel method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of controllable generation on the NuScenes and KITTI datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06109 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models Zhang, Jinhua Sheng, Hualian Cai, Sijia Deng, Bing Liang, Qiao Li, Wen Fu, Ying Ye, Jieping Gu, Shuhang Computer Vision and Pattern Recognition Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the innovative integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a novel method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of controllable generation on the NuScenes and KITTI datasets. |
| title | PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06109 |