ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Jiahui, Wang, Weining, Sun, Mingzhen, Yang, Yirong, Zhu, Xinxin, Liu, Jing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914159813197824
author Sun, Jiahui
Wang, Weining
Sun, Mingzhen
Yang, Yirong
Zhu, Xinxin
Liu, Jing
author_facet Sun, Jiahui
Wang, Weining
Sun, Mingzhen
Yang, Yirong
Zhu, Xinxin
Liu, Jing
contents Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a Projected Latent Diffusion Transformer designed for efficient and synchronized audio-video generation. To address structural inconsistencies, we preprocess raw audio into video-like representations, aligning both the temporal and spatial dimensions between audio and video. At its core, ProAV-DiT adopts a Multi-scale Dual-stream Spatio-Temporal Autoencoder (MDSA), which projects both modalities into a unified latent space using orthogonal decomposition, enabling fine-grained spatiotemporal modeling and semantic alignment. To further enhance temporal coherence and modality-specific fusion, we introduce a multi-scale attention mechanism, which consists of multi-scale temporal self-attention and group cross-modal attention. Furthermore, we stack the 2D latents from MDSA into a unified 3D latent space, which is processed by a spatio-temporal diffusion Transformer. This design efficiently models spatiotemporal dependencies, enabling the generation of high-fidelity synchronized audio-video content while reducing computational overhead. Extensive experiments conducted on standard benchmarks demonstrate that ProAV-DiT outperforms existing methods in both generation quality and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12072
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation
Sun, Jiahui
Wang, Weining
Sun, Mingzhen
Yang, Yirong
Zhu, Xinxin
Liu, Jing
Multimedia
Artificial Intelligence
Sound
Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a Projected Latent Diffusion Transformer designed for efficient and synchronized audio-video generation. To address structural inconsistencies, we preprocess raw audio into video-like representations, aligning both the temporal and spatial dimensions between audio and video. At its core, ProAV-DiT adopts a Multi-scale Dual-stream Spatio-Temporal Autoencoder (MDSA), which projects both modalities into a unified latent space using orthogonal decomposition, enabling fine-grained spatiotemporal modeling and semantic alignment. To further enhance temporal coherence and modality-specific fusion, we introduce a multi-scale attention mechanism, which consists of multi-scale temporal self-attention and group cross-modal attention. Furthermore, we stack the 2D latents from MDSA into a unified 3D latent space, which is processed by a spatio-temporal diffusion Transformer. This design efficiently models spatiotemporal dependencies, enabling the generation of high-fidelity synchronized audio-video content while reducing computational overhead. Extensive experiments conducted on standard benchmarks demonstrate that ProAV-DiT outperforms existing methods in both generation quality and computational efficiency.
title ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation
topic Multimedia
Artificial Intelligence
Sound
url https://arxiv.org/abs/2511.12072