Abstract
User captured photos may inadvertently include passersby, may be captured from a less than optimal angle, exclude the photographer from a group photo, or have other defects. This disclosure describes the use of generative artificial intelligence (AI) models to automatically generate updated photos based on captured photos in response to a user command, e.g., provided as a prompt. The updated photo may change the capture angle (e.g., using NeRF) to improve framing, may remove an unwanted person, or construct group photos that do not exclude the group member taking the photo. To enable removal of unwanted people or addition of group members, users can set their cameras to take multiple successive photos in a burst and provide these to a suitable generative AI model with a suitable prompt. The generative AI models can be fine-tuned for the respective task and may be trained based on high quality photos, e.g., with good framing, lighting, etc.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Johnson Jr, Joseph and Johnson, Quinn, "Removing Undesired Elements and Enhancing Photo Angles Using Artificial Intelligence", Technical Disclosure Commons, (September 01, 2024)
https://www.tdcommons.org/dpubs_series/7325