Total: 1
The fields of 3D reconstruction and text-based 3D editing have advanced significantly with the evolution of text-based diffusion models. While existing 3D editing methods excel at modifying color, texture, and style, they struggle with extensive geometric or appearance changes, thus limiting their applications. We propose \textbf{Perturb-and-Revise}, which makes possible a variety of NeRF editing. First, we \textbf{perturb} the NeRF parameters with random initializations to create a versatile initialization. We automatically determine the perturbation magnitude through analysis of the local loss landscape. Then, we \textbf{revise} the edited NeRF via generative trajectories. Combined with the generative process, we impose identity-preserving gradients to refine the edited NeRF. Extensive experiments demonstrate that Perturb-and-Revise facilitates flexible, effective, and consistent editing of color, appearance, and geometry in 3D without model retraining.