arXiv:2609.23817v1 Announce Type: new Abstract: We present VISTA, a two-stage framework for generating stylized 3D human motion by fusing structural content from text prompts with expressive style fr...
The paper introduces a two-stage framework to incorporate the animation principle of exaggeration into motion generative models. During training, it fine‑tunes pre‑trained text‑to‑motion models on a curated exaggeration dataset. At inference, it uses a mathematical formulation based on dynamic movement primitives to guide diffusion and flow‑matching models toward more expressive, exaggerated motions while maintaining physical plausibility and the original motion intent.
The paper introduces Motion Style Slider, a framework that enables continuous, endpoint‑supervised control of style intensity in human motion diffusion. By constructing a style direction in a learned motion‑style embedding space and conditioning diffusion generation with a scalar intensity, the method achieves smooth, monotonic style scaling without needing intermediate‑intensity ground truth. The approach is compatible with pretrained diffusion backbones, supports heterogeneous style datasets, and is evaluated on controllability, interpolation/extrapolation, content preservation, and motion realism.
arXiv:2412.00112v5 Announce Type: replace Abstract: Generating natural and expressive human motions from textual descriptions is challenging due to the complexity of coordinating full-body dynamics a...
arXiv:2606. 22726v2 Announce Type: replace Abstract: Choreographic motion generation poses unique challenges for AI, demanding precise semantic control over complex, temporally structured, and expressive full-body dynamics.
The paper introduces ELMA, a new episodic long‑term motion dataset designed to benchmark anaphoric compositions in text‑to‑motion generation. ELMA contains densely annotated 30‑second clips extracted from in‑the‑wild videos, preserving cross‑segment dependencies that current models struggle to handle. Fine‑tuning state‑of‑the‑art models on ELMA improves both global physical realism and semantic alignment, establishing a robust baseline for long‑term motion synthesis.
STyMo is a few‑shot motion style transfer method that learns from only seconds of paired data and trains in one to two minutes. It decomposes style into a static posture component and a temporal dynamics component, allowing runtime adjustment of posture intensity, temporal exaggeration, and per‑body‑region style. The approach includes a stylizability gate to avoid artifacts on out‑of‑distribution motions and supports an iterative authoring workflow, with results shown across a range of motion styles and a released dataset for future research.
arXiv:2609.23797v1 Announce Type: cross Abstract: Human motion is shaped by both external acoustic events and behavioral intent: spatial audio conveys environmental cues that elicit or guide a respon...
The paper introduces SMART, a Self‑evolving Multi‑Agent Refinement Framework for conversational text‑to‑motion generation. It enables users to iteratively refine specific spatio‑temporal regions of a motion sequence based on natural language feedback, preserving the rest of the motion. The framework incorporates a semantic‑guided masked editing mechanism and a memory‑based self‑evolving strategy to reuse past editing knowledge and reduce redundant exploration.
arXiv:2606. 01014v1 Announce Type: cross Abstract: We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language.
BiMoGen introduces a unified masked discrete diffusion framework for bidirectional motion‑text generation, addressing the limitations of autoregressive models in capturing bidirectional dependencies between language and motion. The approach employs a two‑stage training strategy—decoupled uni‑ and cross‑modal pretraining followed by supervised fine‑tuning—to establish robust cross‑modal correspondence, and incorporates Generation‑Aware Self‑Correction to mitigate error propagation during inference. Experiments on HumanML3D and KIT‑ML show competitive performance on both text‑to‑motion and motion‑to‑text tasks, demonstrating the effectiveness of the proposed training and correction mechanisms.
arXiv:2601. 08828v2 Announce Type: replace-cross Abstract: Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood.