Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models (2306.17203v1)

Published 29 Jun 2023 in cs.SD, cs.CV, cs.LG, and eess.AS

Abstract: The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semantically aligned features, then train an LDM with CAVP-aligned visual features on spectrogram latent space. The CAVP-aligned features enable LDM to capture the subtler audio-visual correlation via a cross-attention module. We further significantly improve sample quality with `double guidance'. Diff-Foley achieves state-of-the-art V2A performance on current large scale V2A dataset. Furthermore, we demonstrate Diff-Foley practical applicability and generalization capabilities via downstream finetuning. Project Page: see https://diff-foley.github.io/

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Vanessa Theme Ament. The Foley grail: The art of performing sound for film, games, and animation. Routledge, 2021.
  2. Vggsound: A large-scale audio-visual dataset. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 721–725. IEEE, 2020.
  3. Generating visually aligned sound from videos. IEEE Transactions on Image Processing, 29:8292–8302, 2020.
  4. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  5. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34:8780–8794, 2021.
  6. Clap learning audio concepts from natural language supervision. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE, 2023.
  7. Structure and content-guided video synthesis with diffusion models. arXiv preprint arXiv:2302.03011, 2023.
  8. Slowfast networks for video recognition. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6202–6211, 2019.
  9. Audio set: An ontology and human-labeled dataset for audio events. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 776–780. IEEE, 2017.
  10. Signal estimation from modified short-time fourier transform. IEEE Transactions on acoustics, speech, and signal processing, 32(2):236–243, 1984.
  11. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020.
  12. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  13. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303, 2022.
  14. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  15. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022.
  16. Video diffusion models. arXiv preprint arXiv:2204.03458, 2022.
  17. Neural dubber: dubbing for videos according to scripts. Advances in neural information processing systems, 34:16582–16595, 2021.
  18. EPIC-SOUNDS: A Large-Scale Dataset of Actions that Sound. In IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP), 2023.
  19. Taming visually guided sound generation. arXiv preprint arXiv:2110.08791, 2021.
  20. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950, 2017.
  21. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis. Advances in Neural Information Processing Systems, 33:17022–17033, 2020.
  22. Panns: Large-scale pretrained audio neural networks for audio pattern recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28:2880–2894, 2020.
  23. Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761, 2020.
  24. Melgan: Generative adversarial networks for conditional waveform synthesis. Advances in neural information processing systems, 32, 2019.
  25. Audioldm: Text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503, 2023.
  26. Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778, 2022.
  27. Fixing weight decay regularization in adam. 2017.
  28. Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095, 2022.
  29. ALYSSA MAIO. What is a foley artist — how to bring movies to life with sound, 2022. https://www.studiobinder.com/blog/what-is-a-foley-artist/.
  30. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741, 2021.
  31. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499, 2016.
  32. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
  33. Visually indicated sounds. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2405–2413, 2016.
  34. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  35. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  36. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10684–10695, 2022.
  37. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35:36479–36494, 2022.
  38. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402, 2022.
  39. I hear your true colors: Image guided audio generation. arXiv preprint arXiv:2211.03089, 2022.
  40. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning, pages 2256–2265. PMLR, 2015.
  41. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2020.
  42. Maximum likelihood training of score-based diffusion models. Advances in Neural Information Processing Systems, 34:1415–1428, 2021.
  43. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
  44. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
  45. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  46. Diffsound: Discrete diffusion model for text-to-sound generation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023.
  47. Visual to sound: Generating natural sound for videos in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3550–3558, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Simian Luo (9 papers)
  2. Chuanhao Yan (1 paper)
  3. Chenxu Hu (12 papers)
  4. Hang Zhao (156 papers)
Citations (64)
View on Semantic Scholar
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. Diff-Foley