CVPR2024
Shap-Editor: Instruction-guided Latent 3D Editing in Seconds
Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
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.