Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

• URL: http://arxiv.org/abs/2512.02457v2
• Date: Wed, 03 Dec 2025 02:53:53 GMT
• Title: Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
• Authors: Jianzong Wu, Hao Lian, Dachao Hao, Ye Tian, Qingyu Shi, Biaolong Chen, Hao Jiang, Yunhai Tong,
• Abstract summary: We introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising.<n>Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony.
• Score: 20.446421146630474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent audio-video generative systems suggest that coupling modalities benefits not only audio-video synchrony but also the video modality itself. We pose a fundamental question: Does audio-video joint denoising training improve video generation, even when we only care about video quality? To study this, we introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising. We train (i) a T2AV model with AVFullDiT and (ii) a T2V-only counterpart under identical settings. Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony. We observe consistent improvements on challenging subsets featuring large and object contact motions. We hypothesize that predicting audio acts as a privileged signal, encouraging the model to internalize causal relationships between visual events and their acoustic consequences (e.g., collision $\times$ impact sound), which in turn regularizes video dynamics. Our findings suggest that cross-modal co-training is a promising approach to developing stronger, more physically grounded world models. Code and dataset will be made publicly available.

Related papers

• ALIVE: Animate Your World with Lifelike Audio-Video Generation [50.693986608051716]
  ALIVE is a generation model that adapts a pretrained Text-to-Video (T2V) model to Sora-style audio-video generation and animation.<n>To support the audio-visual synchronization and reference animation, we augment the popular MMDiT architecture with a joint audio-video branch.<n>ALIVE demonstrates outstanding performance, consistently outperforming open-source models and matching or surpassing state-of-the-art commercial solutions.
  arXiv  Detail & Related papers  (2026-02-09T14:06:03Z)
• Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance [33.1393328136321]
  We propose a step-by-step video-to-audio (V2A) generation method for finer controllability over the generation process and more realistic audio synthesis.<n>Inspired by traditional Foley, our approach aims to capture all sound events induced by a video through the incremental generation of missing sound events.
  arXiv  Detail & Related papers  (2025-06-26T04:20:08Z)
• AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation [49.6922496382879]
  We propose a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation.<n>The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models.
  arXiv  Detail & Related papers  (2024-12-19T18:57:21Z)
• VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation [27.9571263633586]
  We introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation.<n>Our framework comprises two key components: a Visual-Text and a Joint VT-SiT model.<n>Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds.
  arXiv  Detail & Related papers  (2024-12-14T09:36:10Z)
• Audio-visual training for improved grounding in video-text LLMs [1.9320359360360702]
  We propose a model architecture that handles audio-visual inputs explicitly. We train our model with both audio and visual data from a video instruction-tuning dataset. For better evaluation of audio-visual models, we also release a human-annotated benchmark dataset.
  arXiv  Detail & Related papers  (2024-07-21T03:59:14Z)
• Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation [89.96013329530484]
  We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. We utilize an existing text-conditioned video generation model and a pre-trained audio encoder model. We validate our method extensively on three datasets demonstrating significant semantic diversity of audio-video samples.
  arXiv  Detail & Related papers  (2023-09-28T13:26:26Z)
• Exploring the Role of Audio in Video Captioning [59.679122191706426]
  We present an audio-visual framework, which aims to fully exploit the potential of the audio modality for captioning. We propose new local-global fusion mechanisms to improve information exchange across audio and video.
  arXiv  Detail & Related papers  (2023-06-21T20:54:52Z)
• MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation [70.74377373885645]
  We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously. MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Experiments show superior results in unconditional audio-video generation, and zero-shot conditional tasks.
  arXiv  Detail & Related papers  (2022-12-19T14:11:52Z)
• Generating Visually Aligned Sound from Videos [83.89485254543888]
  We focus on the task of generating sound from natural videos. The sound should be both temporally and content-wise aligned with visual signals. Some sounds generated outside of a camera can not be inferred from video content.
  arXiv  Detail & Related papers  (2020-07-14T07:51:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.