Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
CameraBench is a dataset for understanding camera motions in videos, created by syCen. It includes approximately 1,400 annotated video clips used for fine-tuning models like Qwen2.5-VL. The dataset supports evaluation of Structure-from-Motion, Visual Language Models, and scene-aware semantic analysis.
The full dataset description and specifics are available only on the Hugging Face dataset page; key details like columns, sample data, and license are not provided in this summary.