🛰️ Daily AI Frontier
‹ back to 2026-07-16

Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data

Research Multimodal & Generative

Merged summary

TL;DR — Cyclone is a latent diffusion framework for editing weather conditions in driving imagery without paired training data, aiming to improve autonomous-driving perception robustness across adverse conditions.

  • Uses latent diffusion with cycle-consistent constraints plus knowledge from image-text models to synthesize multiple weather conditions across diverse scenes, removing the need for paired data.
  • Claims more realistic, structure-preserving outputs than existing baselines (vs. synthetic augmentation or physics-based, task-specific methods).
  • Reports consistent gains on several downstream driving perception tasks.
  • Can be distilled into a video diffusion model for temporally consistent weather editing.

Sources (1)

Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data

arXiv cs.CV Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez, Nathan Piasco, Dzmitry Tsishkou, Laurent Caraffa, Jean-Philippe Tarel, Roland Brémond 2026-07-15 arXiv:2607.13927

TL;DR — Cyclone is a latent diffusion framework for editing weather conditions in driving imagery without paired training data, aiming to improve autonomous-driving perception robustness across adverse conditions.

  • Uses latent diffusion with cycle-consistent constraints plus knowledge from image-text models to synthesize multiple weather conditions across diverse scenes, removing the need for paired data.
  • Claims more realistic, structure-preserving outputs than existing baselines (vs. synthetic augmentation or physics-based, task-specific methods).
  • Reports consistent gains on several downstream driving perception tasks.
  • Can be distilled into a video diffusion model for temporally consistent weather editing.
item →