Preprint
Sep 2026
Tree-Structured Vector Quantization For Efficient And Progressive Image Compression
Tree-VQ is proposed, a progressive tree-structured vector quantization framework for learned image compression that codes progressive continuation decisions and routed branch refinements using only causally available decoded contexts and achieves a superior performance--efficiency trade-off.
Xin-Kun Wang, Tian-Yi Xu, Qing-Yu Luo et al.
· 0 citations