Saved in:
Bibliographic Details
Main Authors: Bernal-Berdun, Edurne, Serrano, Ana, Masia, Belen, Gadelha, Matheus, Hold-Geoffroy, Yannick, Sun, Xin, Gutierrez, Diego
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.12910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929684128727040
author Bernal-Berdun, Edurne
Serrano, Ana
Masia, Belen
Gadelha, Matheus
Hold-Geoffroy, Yannick
Sun, Xin
Gutierrez, Diego
author_facet Bernal-Berdun, Edurne
Serrano, Ana
Masia, Belen
Gadelha, Matheus
Hold-Geoffroy, Yannick
Sun, Xin
Gutierrez, Diego
contents 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. Our data, model, and code are publicly available at https://graphics.unizar.es/projects/PreciseCam2024.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12910
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PreciseCam: Precise Camera Control for Text-to-Image Generation
Bernal-Berdun, Edurne
Serrano, Ana
Masia, Belen
Gadelha, Matheus
Hold-Geoffroy, Yannick
Sun, Xin
Gutierrez, Diego
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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. Our data, model, and code are publicly available at https://graphics.unizar.es/projects/PreciseCam2024.
title PreciseCam: Precise Camera Control for Text-to-Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2501.12910