Summary of Photobot: Reference-guided Interactive Photography Via Natural Language, by Oliver Limoyo et al.
PhotoBot: Reference-Guided Interactive Photography via Natural Language
by Oliver Limoyo, Jimmy Li, Dmitriy Rivkin, Jonathan Kelly, Gregory Dudek
First submitted to arxiv on: 19 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary PhotoBot is a framework for fully automated photo acquisition that combines high-level human language guidance with a robot photographer. The system communicates photography suggestions to the user via reference images selected from a curated gallery, leveraging visual and large language models to characterize the reference images through textual descriptions. A vision transformer captures semantic similarity across marked appearance variations, allowing the computation of suggested pose adjustments for an RGB-D camera by solving a perspective-n-point problem. Our approach demonstrates improved aesthetic quality in photos taken by PhotoBot compared to those taken by users themselves, as measured by human feedback. Additionally, we show that PhotoBot can generalize to other reference sources such as paintings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PhotoBot is a new way for robots to take great pictures. It uses words and computer vision to figure out what would make the best photo. You can tell it what you want using language, like a chatbot. Then, it takes the picture for you! In tests, people liked the photos taken by PhotoBot more than ones they took themselves. This technology could even work with art, like paintings. |
Keywords
* Artificial intelligence * Vision transformer
