Skip to content
Conference Open access

Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion

Sep 2026 · European Conference on Computer Vision · Vol abs/2609.30795, pp. 115-133 · 0 citations · 47 references
Computer Science

TL;DR

This work proposes Motion Style Slider, a motion-to-motion style transfer framework for endpoint-supervised continuous control, which combines diffusion denoising with latent intensity regularization to encourage smooth and monotonic style scaling without requiring intermediate-intensity ground-truth motions.

Abstract

Existing human motion diffusion methods provide strong motion generation quality, and recent style transfer models can inject target style cues, but fine-grained continuous control of style intensity remains underexplored. In production, style intensity is subjective across artists and directors, so the practical requirement is not a universal absolute unit, but a reliable monotonic control axis. We propose Motion Style Slider, a motion-to-motion style transfer framework for endpoint-supervised continuous control. Given a content motion and a style motion, we construct a style direction in a learned motion-style embedding space and condition diffusion generation with a scalar intensity. The training objective combines diffusion denoising with latent intensity regularization to encourage smooth and monotonic style scaling without requiring intermediate-intensity ground-truth motions. Our framework is compatible with pretrained motion diffusion backbones and supports heterogeneous style datasets, including the multi-actor style motion dataset. To test out-of-range usability, we additionally introduce a small real-capture over-reaction extension and evaluate large-intensity behavior against these unseen targets. Experiments measure controllability, interpolation/extrapolation behavior, content preservation, and motion realism, with ablations on direction construction and loss design.

Read PDF

Similar papers

#artificial intelligence Preprint Oct 2026

LociArt: A Unified Paradigm for Free-Style Local Video Stylization

Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies where to stylize and what style to apply whi...

Yuxuan Chen, Feng Xie, Jia-Gao Hu et al. · 0 citations
Book Open access Nov 2026

COME: Advancing Motion Representation and Generative Modeling for High-Quality Text-to-Motion

Text-to-Motion generation aims to synthesize 3D human motion from natural language. While diffusion models naturally capture motion continuity, they often underperform discrete token-based approaches. Emerging applications such as motion editing and multimodal control, however, require fine-grained control, composition...

Guangtao Lyu, Xin-Yi Cheng, Qi Liu et al. · 0 citations
Sep 2026

VISTA: Video-Injected Stylized Text-to-Animation

VISTA achieves the highest style recognition accuracy among video-conditioned methods while preserving competitive content alignment, and its decomposed 3-way classifier-free guidance provides independent, user-controllable calibration of the content-style balance at inference time.

Monseej Purkayastha, Anindita Ghosh, Philipp Slusallek · 0 citations
Oct 2026

Motion Controlled Text-to-4D Generation with Multi-View Video Diffusion Model.

Recent advances in 2D and 3D generative modeling have paved the way for 4D generation. However, existing methods predominantly focus on text-to-4D generation, emphasizing temporal smoothness and spatial consistency while often neglecting precise motion control. Furthermore, due to the inherent ambiguity of text descrip...

Run-Xin Liu, Yang Chen, Ying-Wei Pan et al. · 0 citations
Sep 2026

Depth-Adaptive Injection for Stylized Text-to-Motion.

Discrete text-to-motion generation models are powerful tools for synthesizing diverse human motions, yet endowing them with controllable, high-fidelity stylistic variations remains challenging. Direct retraining or fine-tuning these models often disrupts the fragile discrete token distributions learned by masked genera...

Shuai-Ying Hou, Hong-Yu Tao, Jun-Jie Gao et al. · 0 citations
Preprint Oct 2026

TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer

Reference-guided style transfer aims to preserve the semantic structure of a content image while transferring the visual appearance of a style reference. Recent diffusion-based methods achieve impressive stylization quality by exploiting strong pretrained generative priors. However, training-free approaches still face...

Duc Khoan Le, Kim Ngoc Tran, Minh Đức Nhật Lê et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.