Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Hunyuan3D-Buffalo 1.0:用于可扩展3D生成、理解与编辑的统一多模态模型
机构 * Tencent Hunyuan(腾讯混元)
专题命中 3D生成 :3D generation(title,abstract);spatial understanding(abstract);分类 cs.CV
AI总结 Hunyuan3D-Buffalo 1.0是支持3D理解、文本到3D生成等功能的统一多模态模型,构建87M规模语料库训练,在相关基准上达SOTA或领先性能,验证了统一训练的有效性。
Comments Project Page: https://tencent-hunyuan.github.io/Hunyuan3D-Buffalo1.0