Metraipolis › archive › dc_c61ec0b152fa
Rethinking Radar 3D Perception: Representation Learning from Raw Spectra — arXiv:2611.12334
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12334
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:50.914Z
- SHA-256 of the archived text
34cf99f9adc64b860a973d45fd5536635231ae47c7cd3f9d2c7622d64be8cbdd- Stable URL of this page
https://metraipolis.com/documento/dc_c61ec0b152fa
How to cite
Rethinking Radar 3D Perception: Representation Learning from Raw Spectra — arXiv:2611.12334 — arXiv (en), https://arxiv.org/abs/2611.12334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c61ec0b152fa (Metraipolis archive dc_c61ec0b152fa, sha256 34cf99f9adc64b860a973d45fd5536635231ae47c7cd3f9d2c7622d64be8cbdd)
BibTeX
@misc{dcc61ec0b152fa,
title = {Rethinking Radar 3D Perception: Representation Learning from Raw Spectra — arXiv:2611.12334},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12334},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c61ec0b152fa; sha256 34cf99f9adc64b860a973d45fd5536635231ae47c7cd3f9d2c7622d64be8cbdd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Raw radar spectra are widely viewed as too cluttered and noisy for direct representation learning, motivating handcrafted reductions, sparse point clouds, or compact Doppler descriptors in radar perception. We challenge this assumption and argue that the main limitation lies not in the raw representation itself, but in the absence of a learning objective that separates structured signal from noise. Handcrafted reductions partially address this problem but impose rigid assumptions about what constitutes signal, discarding weak yet informative structure while retaining artifacts that fit the reduction model. Once removed, such information cannot be recovered by supervised learning. We propose an alternative: structure is the component of a radar spectrum that remains reconstructable under localized corruption, while noise is the component that does not. This perspective motivates self-supervised masked modeling for dense radar spectra without predefined signal-noise separation. We instantiate it with Leakage-aware Spectral MAE, a masked autoencoder for raw radar cubes using a corruption strategy inspired by cross-bin energy spreading caused by spectral leakage. We also demonstrate the importance of Doppler organization: treating Doppler as a primary spatial dimension in an x-y-D representation, with height encoded as features, substantially outperforms naive channel stacking and enables effective learning from dense 4D spectra. Without handcrafted reductions, our approach consistently outperforms state-of-the-art radar-based detectors and point-cloud-based self-supervised learning (SSL) counterparts. These results establish raw radar spectra as an effective representation for 3D perception when paired with an appropriate pretraining objective. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2611.12334 — 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 2026-11-10T18:37:37.547Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).