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

In recent times, the generation of 3D assets from text prompts has shownimpressive results. Both 2D and 3D diffusion models can help generate decent 3Dobjects based on prompts. 3D diffusion models have good 3D consistency, buttheir quality and generalization are limited as trainable 3D data is expensiveand hard to obtain. 2D diffusion models enjoy strong abilities ofgeneralization and fine generation, but 3D consistency is hard to guarantee.This paper attempts to bridge the power from the two types of diffusion modelsvia the recent explicit and efficient 3D Gaussian splatting representation. Afast 3D object generation framework, named as GaussianDreamer, is proposed,where the 3D diffusion model provides priors for initialization and the 2Ddiffusion model enriches the geometry and appearance. Operations of noisy pointgrowing and color perturbation are introduced to enhance the initializedGaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3Davatar within 15 minutes on one GPU, much faster than previous methods, whilethe generated instances can be directly rendered in real time. Demos and codeare available at https://taoranyi.com/gaussiandreamer/.

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models