Point cloud upsampling is essential for 3D applications but remains challenging due to sparse, under-constrained observations. Multi-view images can resolve geometric ambiguity, but existing multi-modal methods do not fully exploit visual cues. We propose ControlFlow3D, a framework that distills knowledge from pretrain...
Yuang Liu, Zhi Zuo, Zheng-Kai Zhao et al.· 0 citations
This work proposes Disco4D, a self-disentangled pre-training to extract expressive 4D representations, to separate motion learning in the high-level latent space of the MAE bottleneck while performing geometric reconstruction in the low-level Euclidean space.
Zhi Zuo, Chen-Yi Zhuang, Pan Gao et al.· International Journal of Com...· 0 citations
Function-Room Generation is introduced, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts, and ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, ge...
Hao Feng, Zhi Zuo, Ming-Jian Liang et al.· 1 citation
The results show that the proposed SkelGen4D weakly supervised skeleton modeling matches or surpasses fully supervised baselines while scaling to diverse object categories for high-quality text-driven mesh animation.
Hao Feng, Zhi Zuo, Jia-Hui Pan et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
