FIRM, a Fine-grained Intra-token Representation of Masks, achieves leading results, including $70.5/80.5/80.5$ gIoU/cIoU on LaSeRS and a $3.0-point average gain on EarthReason.
Weidong Tang, Kai-Yu Li, Yi-Kai Wang et al.· 0 citations
Reconstructing editable parametric CAD models from a single-view image is of great practical value for modern manufacturing, yet remains challenging due to incomplete geometric observations and complex inter-part relationships. To address it, we propose CADForge, an agentic framework that progressively converts a singl...
Ke-Yang Lu, Zhifei Yang, Tian-Ao Dong et al.· 0 citations
A unified taxonomy that categorized existing methods into three primary paradigms: Interactive Generation, Interactive Editing, and Embodied Interaction is proposed that categorized existing methods into three primary paradigms and discussed their advantages and limitations.
Yu-Qi Li, Si-Wei Meng, Chuan-Guang Yang et al.· Proceedings of the Thirty-Fi...· 40 citations· ⚡1
StateFlow is presented, a state-centric framework for generative previsualization that uses an editable 3D world to organize scene structure, evolution, and cameras, while off-the-shelf video models enhance visual quality when higher fidelity is desired.
Yuyang Yin, Zixiang Li, Longxiulin Deng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.