ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression 文章

ArXiv CS.CV2026-06-02NEWSen作者: Haisheng Fu, Runyu Yang, Feng Ding, Siyu Zhu, Jie Liang, Xiaoxiao Li, Zhenman Fang, Jingning Han
大语言模型
查看原文 →
关系图谱

ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression · 相关技术

相关技术

windowed spatial self-attentionhybrid CNN-transformer architecturesChannel-wise Wavelet-Domain Transformer Blockchannel-wise wavelet-domain transformer attentionChWDTBChWDTAchannel-wise wavelet transformsTransformer architecturelearned image compression