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

Recently, there has been a significant advancement in text-to-image diffusionmodels, leading to groundbreaking performance in 2D image generation. Theseadvancements have been extended to 3D models, enabling the generation of novel3D objects from textual descriptions. This has evolved into NeRF editingmethods, which allow the manipulation of existing 3D objects through textualconditioning. However, existing NeRF editing techniques have faced limitationsin their performance due to slow training speeds and the use of loss functionsthat do not adequately consider editing. To address this, here we present anovel 3D NeRF editing approach dubbed ED-NeRF by successfully embeddingreal-world scenes into the latent space of the latent diffusion model (LDM)through a unique refinement layer. This approach enables us to obtain a NeRFbackbone that is not only faster but also more amenable to editing compared totraditional image space NeRF editing. Furthermore, we propose an improved lossfunction tailored for editing by migrating the delta denoising score (DDS)distillation loss, originally used in 2D image editing to the three-dimensionaldomain. This novel loss function surpasses the well-known score distillationsampling (SDS) loss in terms of suitability for editing purposes. Ourexperimental results demonstrate that ED-NeRF achieves faster editing speedwhile producing improved output quality compared to state-of-the-art 3D editingmodels.

ED-NeRF: Efficient Text-Guided Editing of 3D Scene using Latent Space NeRF