Metraipolis › archive › dc_1704fb41727f

BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion — arXiv:2610.12307

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12307
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:51.246Z
SHA-256 of the archived text
643ea68720a7ddd7bd44f500a854d3ff6893938a6d46d5c084371fb0d03b5fcf
Stable URL of this page
https://metraipolis.com/documento/dc_1704fb41727f

How to cite

BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion — arXiv:2610.12307 — arXiv (en), https://arxiv.org/abs/2610.12307 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1704fb41727f (Metraipolis archive dc_1704fb41727f, sha256 643ea68720a7ddd7bd44f500a854d3ff6893938a6d46d5c084371fb0d03b5fcf)
BibTeX
@misc{dc1704fb41727f,
  title = {BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion — arXiv:2610.12307},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12307},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1704fb41727f; sha256 643ea68720a7ddd7bd44f500a854d3ff6893938a6d46d5c084371fb0d03b5fcf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12307. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to different resource constraints at inference time, and yields suboptimal quality-cost tradeoff by devoting the same effort to both plain backgrounds and intricate details. We propose BudgetPix, an adaptive tokenization framework that dynamically allocates compute based on visual complexity and spatial layout, enabling flexible computational budgeting at inference time. BudgetPix comprises three key components: (1) an adaptive encoder that maps a fixed-size image to a variable-length token sequence using an entropy-guided quadtree alongside a multi-scale patch embedder; (2) a scale-aware decoder reconstructs fixed-resolution images from multi-scale token sets; and (3) a flexible training and sampling schedule that enables pixel-space denoisers to operate across variable token counts. BudgetPix seamlessly integrates with existing pixel-space diffusion architectures, enabling a single checkpoint to be operated at a wide range of compute budgets. Evaluated on text-to-image generation, BudgetPix matches the fidelity of MiniT2I-L at $512^2$ and PixelDiT at $1024^2$ using just 25% of the original compute budget. In class-conditional generation using a MeanFlow backbone, BudgetPix requires merely 60% of the full compute budget to produce images with near-zero quality degradation, observing a marginal 0.8-point increase in FID. Comprehensive assessments by human and VLM judges confirm that BudgetPix establishes a significantly improved quality-efficiency tradeoff over prior budget-adaptive baselines. More details are available at our project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12307 — 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 2026-10-09T05:55:07.687Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).