Metraipolis › archive › dc_ad860f2a7df2
Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers — arXiv:2609.03641
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03641
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:56:23.201Z
- SHA-256 of the archived text
6e7c71df353de8b59534fb2f92da765dee9a303a84451902686bfeaf24dfabb9- Stable URL of this page
https://metraipolis.com/documento/dc_ad860f2a7df2
How to cite
Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers — arXiv:2609.03641 — arXiv (en), https://arxiv.org/abs/2609.03641 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad860f2a7df2 (Metraipolis archive dc_ad860f2a7df2, sha256 6e7c71df353de8b59534fb2f92da765dee9a303a84451902686bfeaf24dfabb9)
BibTeX
@misc{dcad860f2a7df2,
title = {Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers — arXiv:2609.03641},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03641},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad860f2a7df2; sha256 6e7c71df353de8b59534fb2f92da765dee9a303a84451902686bfeaf24dfabb9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03641. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Progressive image compression requires a single embedded representation whose received prefixes can be decoded without re-encoding the source. Modern vector-quantized (VQ) image models provide strong discrete endpoint representations, but conventional flat codeword indices do not define meaningful intermediate states for a neural decoder. We present Tree-VQ, a post-hoc conversion of a pretrained flat VQ tokenizer into a fine-grained, arbitrary-prefix progressive representation while preserving its encoder assignments and every learned leaf vector. The key idea is to organize the original codebook into a balanced binary hierarchy, associate explicit representations with internal nodes, and transmit branch decisions in depth-major order. Consequently, once the image header is available, every payload prefix uniquely specifies a valid latent state: each additional branch bit refines exactly one token, and transmission can therefore be truncated at essentially any payload position rather than only at a small number of stage boundaries. We further adapt one shared decoder on the complete-depth and mixed-depth latent states encountered under such arbitrary truncation, making these densely spaced prefixes useful for reconstruction rather than merely syntactically decodable. On Kodak, Tree-VQ achieves a DISTS-based BD-rate saving of 52.1% relative to ProGIC, while exposing thousands of valid arbitrary-prefix operating points from a single embedded bitstream. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.03641 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T02:27:18.978Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).