FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips
Mengtian Li, Kunyan Dai, Yi Ding, Ruobing Ni, Ying Zhang, Wenwu Wang, Zhifeng Xie
摘要
Foley art plays a pivotal role in enhancing immersive auditory experiences in film, yet manual creation of spatiotemporally aligned audio remains labor-intensive. We propose FoleyDesigner, a novel framework inspired by professional Foley workflows, integrating film clip analysis, spatio-temporally controllable Foley generation, and professional audio mixing capabilities. FoleyDesigner employs a multi-agent architecture for precise spatio-temporal analysis. It achieves spatio-temporal alignment through latent diffusion models trained on spatio-temporal cues extracted from video frames, combined with large language model (LLM)-driven hybrid mechanisms that emulate postproduction practices in film industry. To address the lack of high-quality stereo audio datasets in film, we introduce FilmStereo, the first professional stereo audio dataset containing spatial metadata, precise timestamps, and semantic annotations for eight common Foley categories. For applications, the framework supports interactive user control while maintaining seamless integration with professional pipelines, including 5.1-channel Dolby Atmos systems compliant with ITU-R BS.775 standards, thereby offering extensive creative flexibility. Extensive experiments demonstrate that our method achieves superior spatio-temporal alignment compared to existing baselines, with seamless compatibility with professional film production standards. The project page is available at https://gekiii996. github.io/FoleyDesigner/.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper17
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran 等NeurIPS 2023 · 被引用 5,068 次
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional DomainsMatthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil 等NeurIPS 2020 · 被引用 4,036 次
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao 等NeurIPS 2024 · 被引用 2,305 次
- Simple and Controllable Music GenerationJade Copet, Felix Kreuk, Itai Gat, Tal Remez 等NeurIPS 2023 · 被引用 843 次
- AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsHaohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei 等ICML 2023 · 被引用 773 次
相关 Paper
- FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured ScriptsYou Li, Dewei Zhou, Fan Ma, Fu Li 等CVPR 2026 · 被引用 2 次
- FilmSceneDesigner: Chaining Set Design for Procedural Film Scene GenerationZhifeng Xie, Keyi Zhang, Yiye Yan, Yuling Guo 等AAAI 2026
- StageDesigner: Artistic Stage Generation for Scenography via Theater ScriptsZhaoxing Gan, Mengtian Li, Ruhua Chen, Zhongxia Ji 等CVPR 2025
- ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and EditingHuadai Liu, Kaicheng Luo, Jialei Wang, Wen Wang 等NeurIPS 2025 · 被引用 5 次
- In-the-wild Audio Spatialization with Flexible Text-guided LocalizationTianrui Pan, Jie Liu, Zewen Huang, Jie Tang 等ACL 2025 · 被引用 2 次
