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

Text-guided diffusion models have revolutionized image and video generationand have also been successfully used for optimization-based 3D objectsynthesis. Here, we instead focus on the underexplored text-to-4D setting andsynthesize dynamic, animated 3D objects using score distillation methods withan additional temporal dimension. Compared to previous work, we pursue a novelcompositional generation-based approach, and combine text-to-image,text-to-video, and 3D-aware multiview diffusion models to provide feedbackduring 4D object optimization, thereby simultaneously enforcing temporalconsistency, high-quality visual appearance and realistic geometry. Our method,called Align Your Gaussians (AYG), leverages dynamic 3D Gaussian Splatting withdeformation fields as 4D representation. Crucial to AYG is a novel method toregularize the distribution of the moving 3D Gaussians and thereby stabilizethe optimization and induce motion. We also propose a motion amplificationmechanism as well as a new autoregressive synthesis scheme to generate andcombine multiple 4D sequences for longer generation. These techniques allow usto synthesize vivid dynamic scenes, outperform previous work qualitatively andquantitatively and achieve state-of-the-art text-to-4D performance. Due to theGaussian 4D representation, different 4D animations can be seamlessly combined,as we demonstrate. AYG opens up promising avenues for animation, simulation anddigital content creation as well as synthetic data generation.

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models