Saved in:
Bibliographic Details
Main Authors: Fang, Pengcheng, Sun, Tengjiao, Fu, Dongjie, Zhan, Xiaoyu, Guo, Yanwen, Kim, Hansung, Cai, Xiaohao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.14716
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911687524745216
author Fang, Pengcheng
Sun, Tengjiao
Fu, Dongjie
Zhan, Xiaoyu
Guo, Yanwen
Kim, Hansung
Cai, Xiaohao
author_facet Fang, Pengcheng
Sun, Tengjiao
Fu, Dongjie
Zhan, Xiaoyu
Guo, Yanwen
Kim, Hansung
Cai, Xiaohao
contents Sparse anchors provide a compact interface for human motion authoring: users specify a few root positions, planar trajectory samples, or body-point targets, while the system synthesizes the full-body motion that completes the under-specified intent. We present AnchorRoute, a sparse-anchor motion synthesis framework that uses anchors as a shared scaffold for both generation and refinement. Before generation, AnchorRoute converts sparse anchors into anchor-condition features and injects the resulting condition memory into a frozen Transition Masked Diffusion prior through AnchorKV and dual-context conditioning. This preserves the generation quality of the pretrained text-to-motion prior while learning sparse spatial control. After generation, the same anchors are evaluated as residuals: their timestamps define refinement intervals, and their residuals determine where correction should be concentrated. RouteSolver then refines the motion by projecting soft-token updates onto anchor-defined piecewise-affine interval bases. This couples generation-time anchor conditioning with residual-routed refinement under one anchor scaffold. AnchorRoute supports root-3D, planar-root, and body-point control within the same formulation. In benchmark evaluations, AnchorRoute outperforms prior sparse-control methods under the sparse keyjoint protocol and consistently improves anchor adherence across control families. The results show that the learned anchor-conditioned generator and RouteSolver refinement are complementary: the generator preserves text-motion quality, while RouteSolver provides a controllable path toward stronger anchor adherence.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14716
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro
Fang, Pengcheng
Sun, Tengjiao
Fu, Dongjie
Zhan, Xiaoyu
Guo, Yanwen
Kim, Hansung
Cai, Xiaohao
Graphics
Computer Vision and Pattern Recognition
Machine Learning
Sparse anchors provide a compact interface for human motion authoring: users specify a few root positions, planar trajectory samples, or body-point targets, while the system synthesizes the full-body motion that completes the under-specified intent. We present AnchorRoute, a sparse-anchor motion synthesis framework that uses anchors as a shared scaffold for both generation and refinement. Before generation, AnchorRoute converts sparse anchors into anchor-condition features and injects the resulting condition memory into a frozen Transition Masked Diffusion prior through AnchorKV and dual-context conditioning. This preserves the generation quality of the pretrained text-to-motion prior while learning sparse spatial control. After generation, the same anchors are evaluated as residuals: their timestamps define refinement intervals, and their residuals determine where correction should be concentrated. RouteSolver then refines the motion by projecting soft-token updates onto anchor-defined piecewise-affine interval bases. This couples generation-time anchor conditioning with residual-routed refinement under one anchor scaffold. AnchorRoute supports root-3D, planar-root, and body-point control within the same formulation. In benchmark evaluations, AnchorRoute outperforms prior sparse-control methods under the sparse keyjoint protocol and consistently improves anchor adherence across control families. The results show that the learned anchor-conditioned generator and RouteSolver refinement are complementary: the generator preserves text-motion quality, while RouteSolver provides a controllable path toward stronger anchor adherence.
title AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro
topic Graphics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.14716