Shap-Editor: Instruction-guided Latent 3D Editing in Seconds

Minghao Chen; Junyu Xie; Iro Laina; Andrea Vedaldi

doi:10.1109/cvpr52733.2024.02498

CVPR2024顶会

Shap-Editor: Instruction-guided Latent 3D Editing in Seconds

Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi

DOI 出版方

2024年份

12顶会引用

摘要

Add a Santa hat to it" "Make it wear a blue sweater " "Make its color look like rainbow" "Make it look like a panda" ～1 sec Figure 1 . Given 3D assets as inputs, SHAP-EDITOR achieves fast 3D editing in just one second by learning a feed-forward mapping in the latent space of a 3D asset generator.