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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

3D scene representations have gained immense popularity in recent years.Methods that use Neural Radiance fields are versatile for traditional taskssuch as novel view synthesis. In recent times, some work has emerged that aimsto extend the functionality of NeRF beyond view synthesis, for semanticallyaware tasks such as editing and segmentation using 3D feature fielddistillation from 2D foundation models. However, these methods have two majorlimitations: (a) they are limited by the rendering speed of NeRF pipelines, and(b) implicitly represented feature fields suffer from continuity artifactsreducing feature quality. Recently, 3D Gaussian Splatting has shownstate-of-the-art performance on real-time radiance field rendering. In thiswork, we go one step further: in addition to radiance field rendering, weenable 3D Gaussian splatting on arbitrary-dimension semantic features via 2Dfoundation model distillation. This translation is not straightforward: naivelyincorporating feature fields in the 3DGS framework leads to warp-leveldivergence. We propose architectural and training changes to efficiently avertthis problem. Our proposed method is general, and our experiments showcasenovel view semantic segmentation, language-guided editing and segment anythingthrough learning feature fields from state-of-the-art 2D foundation models suchas SAM and CLIP-LSeg. Across experiments, our distillation method is able toprovide comparable or better results, while being significantly faster to bothtrain and render. Additionally, to the best of our knowledge, we are the firstmethod to enable point and bounding-box prompting for radiance fieldmanipulation, by leveraging the SAM model. Project website at:https://feature-3dgs.github.io/

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields