GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
This addresses the challenge of multi-view consistent 3D scene editing for applications in computer graphics and vision, representing an incremental improvement over existing methods.
The paper tackles the problem of text-driven editing of 3D scenes reconstructed by 3D Gaussian Splatting, achieving faster editing and higher visual quality than previous state-of-the-art methods.
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.