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

Recent advances in generative modeling have led to promising progress onsynthesizing 3D human motion from text, with methods that can generatecharacter animations from short prompts and specified durations. However, usinga single text prompt as input lacks the fine-grained control needed byanimators, such as composing multiple actions and defining precise durationsfor parts of the motion. To address this, we introduce the new problem oftimeline control for text-driven motion synthesis, which provides an intuitive,yet fine-grained, input interface for users. Instead of a single prompt, userscan specify a multi-track timeline of multiple prompts organized in temporalintervals that may overlap. This enables specifying the exact timings of eachaction and composing multiple actions in sequence or at overlapping intervals.To generate composite animations from a multi-track timeline, we propose a newtest-time denoising method. This method can be integrated with any pre-trainedmotion diffusion model to synthesize realistic motions that accurately reflectthe timeline. At every step of denoising, our method processes each timelineinterval (text prompt) individually, subsequently aggregating the predictionswith consideration for the specific body parts engaged in each action.Experimental comparisons and ablations validate that our method producesrealistic motions that respect the semantics and timing of given text prompts.Our code and models are publicly available at https://mathis.petrovich.fr/stmc.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation