REVIEW 3 cited by
GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recently, impressive results have been achieved in 3D scene editing with text instructions based on a 2D diffusion model. However, current diffusion models primarily generate images by predicting noise in the latent space, and the editing is usually applied to the whole image, which makes it challenging to perform delicate, especially localized, editing for 3D scenes. Inspired by recent 3D Gaussian splatting, we propose a systematic framework, named GaussianEditor, to edit 3D scenes delicately via 3D Gaussians with text instructions. Benefiting from the explicit property of 3D Gaussians, we design a series of techniques to achieve delicate editing. Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians. The Gaussian RoI is further used to control the editing process. Our framework can achieve more delicate and precise editing of 3D scenes than previous methods while enjoying much faster training speed, i.e. within 20 minutes on a single V100 GPU, more than twice as fast as Instruct-NeRF2NeRF (45 minutes -- 2 hours).
Forward citations
Cited by 3 Pith papers
-
GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians
Head avatars are produced by graph-neural-network-generated 3D Gaussians, cutting model size to about 10 MB and improving reported image quality over prior Gaussian-splatting avatars.
-
Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians
Proc-GS constrains 3D Gaussian Splatting with procedural code to extract reusable building assets and assemble new buildings and cities.
-
GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization
A text-driven 3D editing framework that tags 3D Gaussian points via cross-attention and uses SDS plus pseudo-GT guidance to edit only the target region.
Discussion (0). Continue with ORCID to comment.