科技行者 on MSN

三星研究院提出ASAG：让AI画图更靠谱的“逆向思维”新方法

扩散模型就像一个善于画画的艺术家，但有时候它画出来的东西并不够理想。为了让画作更精美，科学家们想出了各种"指导"方法，就像在艺术家身边放一个导师，不断提醒他哪里需要改进。然而，现有的指导方法大多依赖一些经验性的技巧，缺乏坚实的理论基础。这就像一个导师 ...
IEEE

Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation

Abstract: Recent progress in interactive point prompt based Image Segmentation allows to significantly reduce the manual effort to obtain high quality semantic labels. State-of-the-art unsupervised ...
IEEE

SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and ...

Abstract: Data synthesis and augmentation are essential for Sound Event Detection (SED) due to the scarcity of temporally labeled data. While augmentation methods like SpecAugment and Mix-up can ...
GitHub

Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

main (this branch): SVI using Wan 2.1 base model (both SVI 1.0/2.0) svi_wan22 branch: SVI using Wan 2.2 base model (both SVI 2.0/2.0 Pro) SVI 2.0 Pro ComfyUI Workflows and Videos from the Community ...
GitHub

Diffusion Transformers with Representation Autoencoders (RAE)

We present Representation Autoencoders (RAE), a class of autoencoders that utilize pretrained, frozen representation encoders such as DINOv2 and SigLIP2 as encoders with trained ViT decoders. RAE can ...