- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
FACT stylizes videos with a frozen SD1.5. It attenuates low frequencies of the latent at every step, rescales content-to-style attention per U-Net scale (LAS), and edits temporal attention along confidence-weighted CoTracker tracks (CTA), evaluated on 2,400 video-style pair.
Critical strengths
-
It is training-free on one frozen backbone, and the examples keep subjects recognizable while picking up the reference colors and textures.
-
The evaluation is large, and the ablation shows CTA matters. Removing it drops CLIP-F from 0.986 to 0.974, far more than removing the other two parts.
Critical weaknesses
-
The frequency step is close to StyleSSP's low-frequency attenuation. The paper says the difference is doing it at every step (lines 123-125), but there is no comparison with init-only filtering.
-
CTA is a weightted version of OmnimatteZero's track-based temporal attention guidance. Table 2 only removes CTA entirely, so the weighting is never tested against plain averaging, and β is not given.
-
Since n ≤ m_ref at every scale, LAS gives λ ≤ 1, which softens attention, the opposite of the paper's diffuse-attention motivation (lines 204-207). The gain may just be weaker style injection.
Questions for authors
-
Where do the foreground masks come from? If they are dataset annotations, FACT gets an input the baselines don't.
-
StyleMaster (CVPR 2025) addresses the same task. Since you already compare with StyleCrafter, which also needs training, could you add it or explain why not?
-
SD1.5 has no cross-frame attention. How is the temporal attention built, and at which layers and steps is CTA applied?