Metraipolis › archive › dc_fcd3136eab25

Diffusion Trajectory Modeling for Semantic Correspondence — arXiv:2609.15357

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15357
License (as archived): CC0-1.0
Archived: 2026-10-16T01:53:29.428Z
SHA-256 of the archived text: ca95756aa6251a71c13d394f675268e003976b0ef0ebc6236915c77c6bed9692
Stable URL of this page: https://metraipolis.com/documento/dc_fcd3136eab25

How to cite

Diffusion Trajectory Modeling for Semantic Correspondence — arXiv:2609.15357 — arXiv (en), https://arxiv.org/abs/2609.15357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcd3136eab25 (Metraipolis archive dc_fcd3136eab25, sha256 ca95756aa6251a71c13d394f675268e003976b0ef0ebc6236915c77c6bed9692)

BibTeX

@misc{dcfcd3136eab25,
  title = {Diffusion Trajectory Modeling for Semantic Correspondence — arXiv:2609.15357},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15357},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcd3136eab25; sha256 ca95756aa6251a71c13d394f675268e003976b0ef0ebc6236915c77c6bed9692},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models generate images through an iterative diffusion process, and recent studies have demonstrated that the intermediate feature maps produced during this process contain rich visual representations, leading to their adoption across a variety of downstream tasks. However, most existing approaches are limited to either using a single feature map at a specific timestep or aggregating feature maps across multiple timesteps. We observe that intermediate representations in the diffusion process form meaningful trajectories along the time axis. In particular, the representation of each spatial patch evolves progressively throughout the generative process, encoding semantics that are difficult to capture from static snapshots alone. This observation motivates the need to treat diffusion representations as temporally structured trajectories rather than static snapshots. To this end, we propose Diffusion Trajectory Modeling (DTM), a framework that interprets the temporal evolution of each spatial patch as a trajectory and leverages it for semantic correspondence. By effectively modeling patch-wise trajectories generated across multiple timesteps, DTM captures correspondence cues that prior methods are not designed to capture. We further demonstrate empirically that spatially corresponding patches form similar trajectory patterns throughout the diffusion process, suggesting that the temporal axis of diffusion carries semantic information. Experiments on SPair-71k, SPair-U and AP-10K show that DTM achieves strong performance, presenting a new perspective for exploiting diffusion representations from a trajectory-centric viewpoint.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.15357 — 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 2026-10-16T01:25:23.673Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).