- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents RGOR (Reference-Grounded Oral Refinement), a framework that improves the identity consistency of generated lips and teeth through reference-guided generation. The method introduces scattered enrollment references and high-resolution mouth patches to preserve fine details. In addition, the authors introduce a reference-contrastive paired loss and a shape loss to better preserve person-specific mouth appearance.
Critical strengths
- The paper has conducted sufficient experiments and human study, and RGOR has good numerical results on benchmarks.
- The visualization cases show improvements in lip and dental details.
Critical weaknesses
- The comparison may be not fair. It is unclear whether the other baselines were trained on the same dataset.
- I am concerned about the practicality of this work. RGOR performs worse than LatentSync-1.6 on the ood HDTF dataset despite additional training. Moreover, existing methods like InfiniteTalk seem to already handle lip identity consistency well.
Questions for authors
- See weekness.
- Could the authors provide a comparison with InfiniteTalk?