PulseAugur
LIVE 12:26:28
research · [3 sources] ·
2
research

New AI models generate realistic human motion with precise trajectory control

Researchers have developed new methods for generating realistic human motion that accurately follows specified trajectories and textual descriptions. One approach, CMC, uses a two-stage diffusion process to first ensure trajectory adherence and then complete the full-body motion, incorporating a selective inpainting mechanism to improve training. Another method, MSCoT, employs a multi-scale, coarse-to-fine strategy with efficient token guidance and a refinement module for faster, more precise control. A third framework, AnchorRoute, uses sparse anchors as a scaffold for both generation and refinement, integrating a diffusion prior with a residual-based refinement solver to enhance control accuracy while maintaining motion quality. AI

Summary written by gemini-2.5-flash-lite from 3 sources. How we write summaries →

IMPACT Advances in controllable human motion synthesis could significantly impact animation, gaming, and robotics by enabling more realistic and interactive character behaviors.

RANK_REASON Multiple research papers introduce novel methods for human motion generation with trajectory control.

Read on arXiv cs.AI →

COVERAGE [3]

  1. arXiv cs.AI TIER_1 · Changxing Ding ·

    Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation

    Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict between text and trajectory conditions d…

  2. arXiv cs.CV TIER_1 · Ajmal Mian ·

    Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control

    We present MSCoT, a multi-scale, coarse-to-fine model for test-time human motion synthesis and control. Unlike recent approaches that rely on multiple iterative denoising/token-prediction steps, or modules tailored for specific control signals, MSCoT discretizes motion into a mul…

  3. arXiv cs.CV TIER_1 · Xiaohao Cai ·

    AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro

    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 spar…