MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment
MACS:基于上下文意义和语义对齐的多源音频到图像生成
专题命中 可控生成 :image generation(title,abstract);分类 cs.CV、cs.GR
AI总结 MACS通过分离多源音频并利用语义对齐提升音频到图像生成的质量和表现。
Comments Accepted at AAAI 2026. Code available at https://github.com/alxzzhou/MACS