English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

3D editing plays a crucial role in many areas such as gaming and virtualreality. Traditional 3D editing methods, which rely on representations likemeshes and point clouds, often fall short in realistically depicting complexscenes. On the other hand, methods based on implicit 3D representations, likeNeural Radiance Field (NeRF), render complex scenes effectively but suffer fromslow processing speeds and limited control over specific scene areas. Inresponse to these challenges, our paper presents GaussianEditor, an innovativeand efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3Drepresentation. GaussianEditor enhances precision and control in editingthrough our proposed Gaussian semantic tracing, which traces the editing targetthroughout the training process. Additionally, we propose Hierarchical Gaussiansplatting (HGS) to achieve stabilized and fine results under stochasticgenerative guidance from 2D diffusion models. We also develop editingstrategies for efficient object removal and integration, a challenging task forexisting methods. Our comprehensive experiments demonstrate GaussianEditor'ssuperior control, efficacy, and rapid performance, marking a significantadvancement in 3D editing. Project Page:https://buaacyw.github.io/gaussian-editor/

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting