AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro

2026-05-14

AI Summary

This work addresses the challenge of efficiently generating and precisely controlling full-body human motion from sparse anchors—such as root trajectories, planar paths, or keypoints. To this end, the authors propose AnchorRoute, a novel framework that integrates anchor-based conditioning with residual-driven refinement. During generation, anchor conditions are injected into a frozen diffusion prior via AnchorKV and a dual-context mechanism. In the optimization phase, temporal segments are partitioned based on anchor residuals, and local adjustments are performed by RouteSolver over piecewise affine bases. AnchorRoute is the first method to unify conditional guidance from sparse anchors with residual-aware optimization, achieving high-quality text-to-motion synthesis while significantly improving motion adherence to diverse anchor types, outperforming existing approaches.

Abstract

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.

Problem

• human motion synthesis
• sparse control
• anchor-based motion authoring
• motion refinement
• conditional generation

Innovation

• sparse anchors
• masked diffusion
• dual-context conditioning
• residual-routed refinement
• piecewise-affine interval bases