Metraipolis › archive › dc_723648ff719a
Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation — arXiv:2608.29997
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29997
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:17.613Z
- SHA-256 of the archived text
00c6aa7e8dc21daf7b87afa6fb1bed8f16bea40c1bbbb5a304b288e76d95be56- Stable URL of this page
https://metraipolis.com/documento/dc_723648ff719a
How to cite
Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation — arXiv:2608.29997 — arXiv (en), https://arxiv.org/abs/2608.29997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_723648ff719a (Metraipolis archive dc_723648ff719a, sha256 00c6aa7e8dc21daf7b87afa6fb1bed8f16bea40c1bbbb5a304b288e76d95be56)
BibTeX
@misc{dc723648ff719a,
title = {Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation — arXiv:2608.29997},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29997},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_723648ff719a; sha256 00c6aa7e8dc21daf7b87afa6fb1bed8f16bea40c1bbbb5a304b288e76d95be56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete diffusion in image translation and generation. By corrupting data into a pure mask state via a random schedule, the conventional forward process induces a twofold misalignment: spatially, this pure-mask destination entirely discards the rich structural priors of the source image; temporally, the random masking order inherently contradicts the ``easy-first, hard-last'' decoding mechanism used during inference. To address this, DDB constructs a direct and efficient trajectory between domains. Spatially, we introduce a hybrid absorption mechanism that redefines the absorbing state to a stochastic mixture of mask and source tokens, effectively injecting source prior as spatial anchors into the latent space. Temporally, we design an information-guided noise schedule that quantifies semantic variation to prioritize the corruption of high-information regions at earlier timesteps. This ensures the model learns to resolve difficult semantic changes using robust context from invariant regions. Extensive experiments validate the versatility and robustness of our framework across diverse generative paradigms. DDB effectively balances edit alignment with structural fidelity across both text-guided semantic manipulation and pure structural image translation, while inherently complementing text-to-image generation and guaranteeing robust high-quality decoding under extremely low sampling steps. Code and models are available at \href{ this https URL }{ this https URL }.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29997 — 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 2026-10-17T09:28:48.101Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).