Search papers, labs, and topics across Lattice.
SwanSphere, a novel streaming framework, is introduced for high-fidelity spatial audio generation from panoramic videos and text by using a causal autoregressive diffusion transformer architecture. A Spatial Video-Audio Contrastive (SVAC) learning strategy aligns the video encoder with the acoustic domain, and a multi-objective online direct preference optimization (ODPO) scheme enhances spatial perception and multimodal synthesis. Experiments show SwanSphere outperforms existing methods in both video-to-spatial and text-to-spatial audio generation.
SwanSphere achieves real-time, high-fidelity spatial audio generation from panoramic video and text, overcoming the latency and spatial accuracy limitations of existing methods.
Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation. 2) We design a Spatial Video-Audio Contrastive (SVAC) learning strategy to align the video encoder with the acoustic domain, and further employ a multi-objective online direct preference optimization (ODPO) scheme, resulting in strong spatial perception and robust multimodal spatial audio synthesis. 3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions. Experimental results demonstrate that SwanSphere achieves superior performance in both video-to-spatial and text-to-spatial audio generation tasks. Demos can be found at: https://swanaigc.github.io.
