Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual representations for the model to reason over. However, effective formalization is highly n...
Jia-Lu Wang, Rui-Chen Zhang, Xia-Oou Liu et al.· 0 citations
This work presents RefineAny3D, a vision-language model that corrects depth without ever predicting a numerical value, and delivers consistent gains across closed-set detectors, open-vocabulary detectors, and 3D auto-labeling tools, and generalizes to novel categories, scenes, and cameras without retraining.
Zhihao Zhang, Geng-Wei Zhang, Tianlong Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.