Pith. sign in

REVIEW 4 cited by

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.19759 v3 pith:PGLJFHVK submitted 2024-04-30 cs.CV

Wenxun Dai , Ling-Hao Chen , Jingbo Wang , Jinpeng Liu , Bo Dai , Yansong Tang This is my paper
classification cs.CV
keywords motiongenerationlatentmotionlcmmodelreal-timecontrolruntime
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation suffer from significant runtime inefficiency. To address this issue, we first propose the motion latent consistency model (MotionLCM) for motion generation, building on the motion latent diffusion model. By adopting one-step (or few-step) inference, we further improve the runtime efficiency of the motion latent diffusion model for motion generation. To ensure effective controllability, we incorporate a motion ControlNet within the latent space of MotionLCM and enable explicit control signals (i.e., initial motions) in the vanilla motion space to further provide supervision for the training process. By employing these techniques, our approach can generate human motions with text and control signals in real-time. Experimental results demonstrate the remarkable generation and controlling capabilities of MotionLCM while maintaining real-time runtime efficiency.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Distilling frozen Motion-JEPA features into a compact 32-D latent whose geometry is coupled to the decoder lets a standard non-autoregressive flow-matching DiT reach state-of-the-art text-to-motion quality on HumanML3...

  2. MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A semantically aligned latent space plus multi-token cross-attention conditioning sets a new state of the art in text-to-human-motion generation on HumanML3D.

  3. Learning to Understand Body Language from Flight through Robust 3D Avatar Placing

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A new dataset places 3D avatars into real drone video with metric placement, and training on it improves long-range human intent classification by 15–26 points.

  4. ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ANT makes text embeddings change across denoising steps and schedules classifier-free guidance to decay, improving text-motion alignment in diffusion text-to-motion models.

Pith tools