FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
Ranking
Overall
69
Content
80
Popularity
44
Observed public metrics from 1 member.
Merged summary
TL;DR - FARI is a one-step inversion framework for authenticating watermarked diffusion-generated images. It outperforms 50-step DDIM inversion in verification robustness while substantially reducing inference time.
- Exploits the lower curvature of inversion trajectories to compress inversion into one step.
- Prioritizes robustness to external image distortions over minimizing comparatively smaller internal truncation errors.
- Uses lightweight adversarial LoRA fine-tuning of the denoiser to improve watermark extraction.
- Requires approximately 20 minutes of fine-tuning on one NVIDIA RTX A6000 GPU.
Sources (1)
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - FARI is a one-step inversion framework for authenticating watermarked diffusion-generated images. It outperforms 50-step DDIM inversion in verification robustness while substantially reducing inference time.
- Exploits the lower curvature of inversion trajectories to compress inversion into one step.
- Prioritizes robustness to external image distortions over minimizing comparatively smaller internal truncation errors.
- Uses lightweight adversarial LoRA fine-tuning of the denoiser to improve watermark extraction.
- Requires approximately 20 minutes of fine-tuning on one NVIDIA RTX A6000 GPU.