- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
HOHI4D provides approximately 5,000 synthetic sequences of two-person, shared-object interactions. Its reconstruction pipeline accompanies HOHI-VAE's structured representation and HOHI-Diff's text-and-object-conditioned generation, with reported improvements over adapted MDM, MLD, and CHOIS baselines.
Critical strengths
- The task of coordinated interaction between two people and a shared object is interesting and valuable.
- The scalable synthesis pipeline addresses an important interaction-data bottleneck, with refinement improving all three reported reconstruction measures.
- Component ablations, training details, prompt examples, and failure cases provide useful supporting evidence.
Critical weaknesses
- The reconstruction-derived dataset lacks reported independent 3D accuracy validation, leaving its reliability as ground truth uncertain given the apparent jitter and interpenetration in the videos.
- The evaluation relies on 2D overlap and learned embedding metrics without directly measuring 3D pose, trajectory, or contact accuracy, leaving geometric correctness insufficiently established.
Questions for authors
How are the dataset splits separated by object instance and prompt template, and which split is used to train HOHI-CLIP?
Thank you for the clarification and additional evaluations, which help address my main concerns. Please include these results and clearly state the remaining limitations in the revised paper. I maintain my weak acceptance recommendation.