This work contends that the bottleneck in identity preservation is not the scarcity of reference frames, but the lack of a mechanism that faithfully transfers the genuine textures they already contain, and presents EfficientSync, a real-time deformation-based framework that retains reference textures rather than resynt...
Fa-Ting Hong, Run-Zheng Liu, Luchuan Song et al.· arXiv.org· 1 citation
Experiments on BEAT2 show that GestureFAR significantly improves the quality--latency trade-off among streaming-capable methods, preserving strong gesture quality while enabling real-time token-causal generation.
Pin-Xin Liu, Hai-Yang Liu, Jia-Hao Luo et al.· 1 citation· ⚡1
A benchmark that tests the ability of agentic video understanding by asking agents to reconstruct real-world videos as animated Blender scenes, and shows that programmatic reconstruction is a viable test of agentic video understanding, and that semantic retention remains the main challenge.
Y. Y. Tang, D. Shimada, Jia-Yue Meng et al.· 9 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.