ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
ConsDreamer:推进多视图一致性以实现零样本文本到3D生成
机构 * School of Artificial Intelligence, Nanjing University of Information Science and Technology(南京信息工程大学人工智能学院) ; Department of Automation, Tsinghua University(清华大学自动化系) ; Lenovo(联想)
专题命中 3D生成 :3D generation(title,abstract);Gaussian Splatting(abstract);分类 cs.CV
AI总结 ConsDreamer通过消除视图偏差和几何一致性约束,解决多面Janus问题,提升零样本文本到3D生成的多视图一致性。
Comments Accepted by IEEE Transactions on Image Processing, Code is available at: https://github.com/GAInuist/ConsDreamer