# Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model

arXiv: https://arxiv.org/abs/2503.22138 · HTML: https://mlsanity.com/paper/2503.22138/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 13 of 13)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [GANSynth: Adversarial Neural Audio Synthesis](https://mlsanity.com/paper/1902.08710/) (2019)
- [Video Background Music Generation with Controllable Music Transformer](https://mlsanity.com/paper/2111.08380/) (2021)
- [Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation](https://mlsanity.com/paper/2206.07771/) (2022)
- [Neural Compatibility Modeling with Attentive Knowledge Distillation](https://mlsanity.com/paper/1805.00313/) (2018)
- [Long-Term Rhythmic Video Soundtracker](https://mlsanity.com/paper/2305.01319/) (2023)
- [Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation](https://mlsanity.com/paper/2210.09549/) (2022)

## Built on by (most cited first, 5 of 5)

- [TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning](https://mlsanity.com/paper/2601.21135/) (2026)
- [V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation](https://mlsanity.com/paper/2603.11042/) (2026)
- [GACA-DiT: Diffusion-based Dance-to-Music Generation with Genre-Adaptive Rhythm and Context-Aware Alignment](https://mlsanity.com/paper/2510.26818/) (2025)
- [JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions](https://mlsanity.com/paper/2606.01703/) (2026)
- [CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation](https://mlsanity.com/paper/2609.13118/) (2026)

## Abstract (arXiv)

Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and generated output can be achieved by training a time-conditioned U-Net augmented with cross-attention mechanism. In this paper, we focus on the problem of generating music synchronized with rhythmic visual cues of the given dance video. Considering that bi-directional guidance is more beneficial for training a diffusion model, we propose to enhance the quality of generated music and its synchronization with dance videos by adopting both positive rhythmic information and negative ones (PN-Diffusion) as conditions, where a dual diffusion and reverse processes is devised. Specifically, to train a sequential multi-modal U-Net structure, PN-Diffusion consists of a noise prediction objective for positive conditioning and an additional noise prediction objective for negative conditioning. To accurately define and select both positive and negative conditioning, we ingeniously utilize temporal correlations in dance videos, capturing positive and negative rhythmic cues by playing them forward and backward, respectively. Through subjective and objective evaluations of input-output correspondence in terms of dance-music beat alignment and the quality of generated music, experimental results on the AIST++ and TikTok dance video datasets demonstrate that our model outperforms SOTA dance-to-music generation models.