{"ID":5937039,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T14:17:21.672613853Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05148","arxiv_id":"2607.05148","title":"Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection","abstract":"Existing multispectral detectors are limited by discrete spectral processing, a scale-dependent shift in the relative reliability of spectral and spatial cues across pyramid levels, and the lack of explicit rotation-equivariant geometric priors for arbitrarily oriented objects. To tackle these limitations, we propose FressDet, a fully rotation-equivariant spectral-spatial learning framework for multispectral object detection, capable of capturing the continuous, ordered nature of spectral structure and enabling reliable spectral-spatial fusion across pyramid levels under arbitrary in-plane rotations. FressDet integrates three complementary components. Spectral Implicit Warp (SpeIW) enables query-based spectral resampling via a coordinate-conditioned implicit field, yielding a monotone, order-preserving warp. Rotation-Equivariant Consistency Weighting (ReCoW) adaptively fuses spectral and spatial branches based on branch reliability, reinforcing informative cues while suppressing noise across pyramid levels. The oriented-aware head exploits group-indexed features to stably predict oriented objects without parameter replication. Taken together, FressDet learns more discriminative and robust spectral-spatial representations even under rotational perturbations. By achieving state-of-the-art performance with 93% fewer parameters on three public benchmarks, FressDet demonstrates its effectiveness and generalizability.","short_abstract":"Existing multispectral detectors are limited by discrete spectral processing, a scale-dependent shift in the relative reliability of spectral and spatial cues across pyramid levels, and the lack of explicit rotation-equivariant geometric priors for arbitrarily oriented objects. To tackle these limitations, we propose F...","url_abs":"https://arxiv.org/abs/2607.05148","url_pdf":"https://arxiv.org/pdf/2607.05148v1","authors":"[\"Peng Zhang\",\"Tingfa Xu\",\"Shuaihao Han\",\"Jianan Li\"]","published":"2026-07-06T14:29:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}