GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting
This work addresses the need for faster and more efficient 3D object editing for users in graphics and AI, though it is incremental as it builds on existing Gaussian Splatting and diffusion models.
The paper tackles the problem of text-guided editing of 3D objects by introducing GSEdit, a pipeline based on Gaussian Splatting that enables efficient style and appearance editing in minutes on consumer hardware while preserving main details and ensuring viewpoint consistency.
We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models. Our method enables the editing of the style and appearance of 3D objects without altering their main details, all in a matter of minutes on consumer hardware. We tackle the problem by leveraging Gaussian splatting to represent 3D scenes, and we optimize the model while progressively varying the image supervision by means of a pretrained image-based diffusion model. The input object may be given as a 3D triangular mesh, or directly provided as Gaussians from a generative model such as DreamGaussian. GSEdit ensures consistency across different viewpoints, maintaining the integrity of the original object's information. Compared to previously proposed methods relying on NeRF-like MLP models, GSEdit stands out for its efficiency, making 3D editing tasks much faster. Our editing process is refined via the application of the SDS loss, ensuring that our edits are both precise and accurate. Our comprehensive evaluation demonstrates that GSEdit effectively alters object shape and appearance following the given textual instructions while preserving their coherence and detail.