IVC-liuyuan/OmniDiff download history

IVC-liuyuan/OmniDiff is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 884 times (237 in the last 7 days), and 1,661 times in total. It ranks #21,201 among datasets by monthly downloads.

OmniDiff OmniDiff is a benchmark for fine-grained Image Difference Captioning (IDC): given two similar images, a model must describe their subtle visual differences in natural language. The dataset combines complex real-world environments with near-realistic 3D-rendered scenes and emp

Open IVC-liuyuan/OmniDiff on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.