Metraipolis › archive › dc_c3a9cd3e1950
Cyclops: LiDAR as a Camera That Dreams in Color — arXiv:2608.16264
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16264
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T23:06:02.664Z
- SHA-256 of the archived text
fb32830a562573c14af67af40c361eeda41619fb83931f59ad62cb1d1358495c- Stable URL of this page
https://metraipolis.com/documento/dc_c3a9cd3e1950
How to cite
Cyclops: LiDAR as a Camera That Dreams in Color — arXiv:2608.16264 — arXiv (en), https://arxiv.org/abs/2608.16264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3a9cd3e1950 (Metraipolis archive dc_c3a9cd3e1950, sha256 fb32830a562573c14af67af40c361eeda41619fb83931f59ad62cb1d1358495c)
BibTeX
@misc{dcc3a9cd3e1950,
title = {Cyclops: LiDAR as a Camera That Dreams in Color — arXiv:2608.16264},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16264},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3a9cd3e1950; sha256 fb32830a562573c14af67af40c361eeda41619fb83931f59ad62cb1d1358495c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Conventionally, robotic perception relies heavily on cameras due to the rich semantic texture they provide. However, their performance degrades significantly in low-light or high-dynamic-range environments. Conversely, while Light Detection and Ranging (LiDAR) captures illumination-invariant geometric and intensity properties, the resulting data are typically single-channel and sparse, creating a significant modality gap when applying vision models pre-trained on RGB datasets. In this paper, we propose Cyclops, a framework that translates sparse Non-Repetitive Scanning LiDAR (NRS-LiDAR) intensity into RGB video, enabling camera-free inference for all-day perception tasks. Our approach first converts sparse LiDAR intensity projections into dense representations via a frozen pre-trained densification module, serving as a geometrically rich source condition. The dense intensity latent is then transported toward the target RGB distribution through Latent Bridge Matching (LBM) with a learned velocity field in a few ODE integration steps. To mitigate inter-frame flickering, we inject prior-frame context via temporal attention layers and further formulate the velocity field as a policy optimized by a differentiable terminal reward that encourages terminal fidelity through backpropagation along the ODE trajectory. Extensive experiments demonstrate that the synthesized RGB, including those generated under near-dark conditions, enable standard RGB-based perception models to substantially outperform both LiDAR baselines and conventional cameras on semantic segmentation, lane detection, and point cloud colorization across diverse lighting conditions. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.16264 — 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 2026-10-18T23:01:50.381Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).