# PreciseCam: Precise Camera Control for Text-to-Image Generation Source: [PreciseCam: Precise Camera Control for Text-to-Image Generation]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:57:12.719Z Authors: Edurne Bernal-Berdun, Ana Serrano, Belen Masia, Matheus Gadelha, Yannick Hold-Geoffroy, Xin Sun, Diego Gutierrez Published: 2025-01-22T14:37:01.000Z ## 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. Our data, model, and code are publicly available at https://graphics.unizar.es/projects/PreciseCam2024. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Camera-controllable generation on Puffin-Gen 1.0 (test)](): Camera-controllable generation; Puffin-Gen 1.0 (test); Up Vector Mean Error: 18.66. - [Camera-controlled video generation on SpatialVID extreme](): Camera-controlled Video Generation; SpatialVID extreme; PitchErr (abs): 30.88. ## Original sources and implementation [Original paper]() [PDF]()