← Back to all news
arXiv Computer Vision By Jose Luis Ponton, Alexander Winkler, Ladislav Kavan, Yuting Ye, Petr Kadlecek

STyMo: Fast and Controllable Few-Shot Motion Style Transfer

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jul 1

LUNA: Learning Universal 3D Human Animation Beyond Skinning

arXiv:2606. 31981v1 Announce Type: cross Abstract: Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting.

By Peng Li, Rawal Khirodkar, Junxuan Li, Yuan Dong, Chen Cao, Yuan Liu, Wenhan Luo, Yike Guo, Shunsuke Saito
llms
More like this →
arXiv Computer Vision
Aug 21

ID-V2V: Identity-Preserving Video Restylization

arXiv:2607. 22830v2 Announce Type: replace Abstract: In visual storytelling, human performances are central to creative intent and narrative meaning.

By Yuancheng Xu, Mingming He, Pablo Salamanca, Li Ma, Yash Kant, Emmett Steven, Paul Debevec, Ning Yu
More like this →
arXiv Computer Vision
Aug 28

EditaLive! Unified Character Video Editing for Live Streaming

EditaLive! is a new real‑time framework for character video editing in live streaming, built on a pretrained image animation model (Wan‑Animate) that separates appearance from motion. It uses the CharEdit‑50K dataset for reference‑frame editing and video reconstruction, and adapts the model from offline bidirectional to causal streaming generation. A self‑rollout distillation strategy compresses the model into a two‑step sampler, employing fixed RoPE, alignment forcing, and first‑frame preserved sparse attention to reduce appearance drift and achieve low‑latency inference while preserving facial expressions.

By Zhiyuan Li, Chi-Man Pun, Peng-Tao Jiang, Bo Li, Xiaodong Cun
efficiencybenchmarks
More like this →