AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
read the original abstract
Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone pre-trained on image-only data, with only lightweight, newly inserted adapters being trainable. This shared backbone facilitates both audio and video generation. Specifically, the video branch incorporates a trainable temporal attention layer into a frozen pre-trained DiT block for temporal consistency. Additionally, a small number of trainable parameters adapt the image-based DiT block for audio generation. An extra shared DiT block, equipped with lightweight parameters, facilitates feature interaction between audio and visual modalities, ensuring alignment. Extensive experiments on the AIST++ and Landscape datasets demonstrate that AV-DiT achieves state-of-the-art performance in joint audio-visual generation with significantly fewer tunable parameters. Furthermore, our results highlight that a single shared image generative backbone with modality-specific adaptations is sufficient for constructing a joint audio-video generator. Our source code and pre-trained models will be released.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
PhyAVBench supplies the first benchmark and contrastive metric that measures whether text-to-audio-video models respect real-world audio physics across controlled prompt pairs.
-
Inference-Time Scaling for Joint Audio-Video Generation
Presents multi-verifier framework and Adaptive Reward Weighting (ARW) for inference-time scaling in joint audio-video generation, reporting gains in alignment and synchronization on VGGSound and JavisBench-mini.
-
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation, spanning video, audio, shot, and reference dimensions with an adaptive evaluation framework that reaches 91.5% Spearman correlation...
-
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation featuring four dimensions, challenging scenarios, and an adaptive hybrid evaluation framework that achieves 91.5% Spearman correlati...
-
Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding
MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
-
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
-
VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
-
SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning
SyncDPO improves temporal synchronization in video-audio joint generation using DPO with efficient on-the-fly negative sample construction and curriculum learning.
-
AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
-
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
A large-scale, hierarchically-annotated human-centric video dataset and a three-level benchmark (OHBench) are presented, showing that fine-tuning on a subset of the data improves audio-video generation model performance.
-
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
OmniHuman is a new large-scale multi-scene dataset with video-, frame-, and individual-level annotations for human-centric video generation, accompanied by the OHBench benchmark that adds metrics aligned with human pe...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.