PreciseCam: Precise Camera Control for Text-to-Image Generation

Abstract

Images as an artistic medium often rely on specific camera angles and lens distortions to convey ideas or emotions; however, such precise control is missing in current text-to-image models. We propose an efficient and general solution that allows precise control over the camera when generating both photographic and artistic images. Unlike prior methods that rely on predefined shots, we rely solely on four simple extrinsic and intrinsic camera parameters, removing the need for pre-existing geometry, reference 3D objects, and multi-view data.We also present a novel dataset with more than 57,000 images, along with their text prompts and ground-truth camera parameters. Our evaluation shows precise camera control in text-to-image generation, surpassing traditional prompt engineering approaches.

Cite

Text

Bernal-Berdun et al. "PreciseCam: Precise Camera Control for Text-to-Image Generation." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00260

Markdown

[Bernal-Berdun et al. "PreciseCam: Precise Camera Control for Text-to-Image Generation." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/bernalberdun2025cvpr-precisecam/) doi:10.1109/CVPR52734.2025.00260

BibTeX

@inproceedings{bernalberdun2025cvpr-precisecam,
  title     = {{PreciseCam: Precise Camera Control for Text-to-Image Generation}},
  author    = {Bernal-Berdun, Edurne and Serrano, Ana and Masia, Belen and Gadelha, Matheus and Hold-Geoffroy, Yannick and Sun, Xin and Gutierrez, Diego},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {2724-2733},
  doi       = {10.1109/CVPR52734.2025.00260},
  url       = {https://mlanthology.org/cvpr/2025/bernalberdun2025cvpr-precisecam/}
}