Saved in:
Bibliographic Details
Main Authors: Zhang, Yan, Zou, Han, Feng, Lincong, Xie, Cong, Yu, Ruiqi, Zhan, Zhenpeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.11720
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912760164515840
author Zhang, Yan
Zou, Han
Feng, Lincong
Xie, Cong
Yu, Ruiqi
Zhan, Zhenpeng
author_facet Zhang, Yan
Zou, Han
Feng, Lincong
Xie, Cong
Yu, Ruiqi
Zhan, Zhenpeng
contents Recent pose-to-video models can translate 2D pose sequences into photorealistic, identity-preserving dance videos, so the key challenge is to generate temporally coherent, rhythm-aligned 2D poses from music, especially under complex, high-variance in-the-wild distributions. We address this by reframing music-to-dance generation as a music-token-conditioned multi-channel image synthesis problem: 2D pose sequences are encoded as one-hot images, compressed by a pretrained image VAE, and modeled with a DiT-style backbone, allowing us to inherit architectural and training advances from modern text-to-image models and better capture high-variance 2D pose distributions. On top of this formulation, we introduce (i) a time-shared temporal indexing scheme that explicitly synchronizes music tokens and pose latents over time and (ii) a reference-pose conditioning strategy that preserves subject-specific body proportions and on-screen scale while enabling long-horizon segment-and-stitch generation. Experiments on a large in-the-wild 2D dance corpus and the calibrated AIST++2D benchmark show consistent improvements over representative music-to-dance methods in pose- and video-space metrics and human preference, and ablations validate the contributions of the representation, temporal indexing, and reference conditioning. See supplementary videos at https://hot-dance.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2512_11720
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reframing Music-Driven 2D Dance Pose Generation as Multi-Channel Image Generation
Zhang, Yan
Zou, Han
Feng, Lincong
Xie, Cong
Yu, Ruiqi
Zhan, Zhenpeng
Computer Vision and Pattern Recognition
Recent pose-to-video models can translate 2D pose sequences into photorealistic, identity-preserving dance videos, so the key challenge is to generate temporally coherent, rhythm-aligned 2D poses from music, especially under complex, high-variance in-the-wild distributions. We address this by reframing music-to-dance generation as a music-token-conditioned multi-channel image synthesis problem: 2D pose sequences are encoded as one-hot images, compressed by a pretrained image VAE, and modeled with a DiT-style backbone, allowing us to inherit architectural and training advances from modern text-to-image models and better capture high-variance 2D pose distributions. On top of this formulation, we introduce (i) a time-shared temporal indexing scheme that explicitly synchronizes music tokens and pose latents over time and (ii) a reference-pose conditioning strategy that preserves subject-specific body proportions and on-screen scale while enabling long-horizon segment-and-stitch generation. Experiments on a large in-the-wild 2D dance corpus and the calibrated AIST++2D benchmark show consistent improvements over representative music-to-dance methods in pose- and video-space metrics and human preference, and ablations validate the contributions of the representation, temporal indexing, and reference conditioning. See supplementary videos at https://hot-dance.github.io
title Reframing Music-Driven 2D Dance Pose Generation as Multi-Channel Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.11720