Live page · Day archive

Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Read the original at HF Daily Papers

Summary

Venus-DefakerOne2 is a vision-forensics foundation model that detects digital and physical forgeries in images and videos. It achieves state-of-the-art performance across benchmarks including DeepFake faces and AI-generated videos.

Carried by: HF Daily Papers. First seen: .