Metraipolis › archive › dc_7e9b67b26041

Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation — arXiv:2607.21628

Source: arXiv (en)
Original: https://arxiv.org/abs/2607.21628
License (as archived): CC0-1.0
Archived: 2026-11-01T02:43:40.619Z
SHA-256 of the archived text: e9b7ebf74bd8461aceea369d12bd3c15113c46bd3d962279fca8b9923790f30a
Stable URL of this page: https://metraipolis.com/documento/dc_7e9b67b26041

How to cite

Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation — arXiv:2607.21628 — arXiv (en), https://arxiv.org/abs/2607.21628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e9b67b26041 (Metraipolis archive dc_7e9b67b26041, sha256 e9b7ebf74bd8461aceea369d12bd3c15113c46bd3d962279fca8b9923790f30a)

BibTeX

@misc{dc7e9b67b26041,
  title = {Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation — arXiv:2607.21628},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2607.21628},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e9b67b26041; sha256 e9b7ebf74bd8461aceea369d12bd3c15113c46bd3d962279fca8b9923790f30a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2607.21628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-based methods achieve spatial alignment but introduce computationally expensive control modules. Paired-data methods achieve realism but rely on complex synthesis pipelines, often altering scene geometry and semantics. Training-free editing methods avoid both constraints but lack a learned appearance prior, limiting their perceptual quality. Recently proposed phase-preserving diffusion presents a promising alternative, but Fourier-domain formulations are constrained by global spectral coupling. This coupling induces spatial artifacts such as ringing and boundary leakage, thereby degrading structural and semantic consistency. We introduce Wavelet Phase Diffusion, which addresses this through two components. First, we operate in the Dual-Tree Complex Wavelet Packet Transform domain, whose localized wavelet packets enable spatially adaptive phase injection without global spectral interference. Second, Low-Frequency Randomization (LFR) replaces the low-frequency packet, decoupling the model from the synthetic illumination prior and enabling in-distribution real-world appearance. Both components train on unpaired open-domain data, and introduce negligible inference overhead. The spatial locality further enables instance-level translation, where individual objects or regions are translated to photorealistic appearance independently while the surrounding scene remains untranslated. On vKITTI $\to$ KITTI image translation, $\psi$-PD outperforms prior methods in realism and semantic consistency while maintaining competitive structural alignment. For CARLA video translation, $\psi$-PD approaches the realism of paired-data methods while reducing VLM planner ADE and FDE by $5.4\%$ and $5.1\%$, respectively.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2607.21628 — 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 2026-11-01T02:16:44.001Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).