Search papers, labs, and topics across Lattice.
This paper introduces SkelGen4D, a weakly supervised framework for generating temporally coherent 3D mesh animations driven by text inputs, which eliminates the need for detailed per-frame skeleton annotations. By recovering pseudo-skeletons from animated meshes through differentiable fitting and generating skeleton motion sequences in a feed-forward manner, the approach ensures both physical plausibility and articulated animation. Evaluations on large-scale benchmarks reveal that SkelGen4D not only matches but often exceeds the performance of fully supervised methods, demonstrating its scalability and flexibility in animation production workflows.
SkelGen4D achieves high-quality text-driven mesh animation without the burden of extensive skeleton annotations, outperforming fully supervised models.
We study 4D generation to synthesize temporally coherent sequences of 3D geometry for animation and content creation. In contrast to existing SDS-based optimization methods and video-driven animation approaches, we adopt a skeleton-driven animation framework aligned with standard industrial pipelines, which enables explicit control and editing. To this end, we propose SkelGen4D, a weakly supervised feed-forward framework for text-driven mesh animation that generates explicit skeleton motions without requiring per-frame skeleton annotations. SkelGen4D first recovers temporally consistent pseudo-skeletons from animated meshes via differentiable fitting, and then generates text-conditioned skeleton motion sequences in a feed-forward manner, further refined with Motion-GRPO to ensure temporally coherent, physically plausible, and articulated animation. We evaluate our method on two large-scale benchmarks, Truebones Zoo and Diffusion4D. Our results show that our weakly supervised skeleton modeling matches or surpasses fully supervised baselines while scaling to diverse object categories for high-quality text-driven mesh animation. Further, our method supports flexible motion editing and is aligned with standard animation production pipelines.
