🤖 AI Summary
Existing approaches struggle to effectively integrate the complementary information from spaceborne optical and SAR imagery, limiting the accuracy of flood mapping. This work proposes a cross-modal multi-task distillation network that simultaneously achieves high-fidelity optical image reconstruction and flood region segmentation within a unified latent space. The method innovatively combines a lightweight optical teacher guidance module, multi-scale windowed cross-attention, FiLM-based conditional modulation, and gated residual connections, alongside a dual-decoder architecture and a hydrologically aware loss function incorporating Charbonnier SSIM, edge-preserving FFT magnitude, and Dice-BCE alignment. Evaluated on SEN1FLOODS11, DEEPFLOOD, and SEN12MS datasets, the approach significantly outperforms current fusion methods in terms of PSNR, SSIM, and LPIPS, markedly enhancing flood mapping quality.
📝 Abstract
Accurate flood water mapping is critical for disaster management, yet current methods struggle to fully exploit the potential of spaceborne imagery. Optical data offers high interpretability but is limited by environmental conditions, whereas SAR provides reliable all-weather coverage with reduced visual interpretability. FLoRA (Fusion Latent for Optical Reconstruction and Area Segmentation) is a cross-modal multi-task framework that jointly reconstructs high-fidelity optical imagery and segments flood water regions from Sentinel 1 SAR by fusing the complementary strengths of optical and SAR data. During training, a lightweight optical teacher (driven by RGB and NDVI priors) provides pyramidal features that guide SAR representations into a fusion latent space via multiscale windowed cross attention and FiLM conditioning, with gated residuals preventing overcorrection. This design enables multi-task learning across two complementary objectives: (a) SAR-to-optical translation for fine-grained RGB reconstruction and (b) flood water region segmentation for hydrologic interpretation. The dual decoders are optimized using Charbonnier SSIM for structural fidelity, edge FFT magnitude losses for spectral realism, and Dice BCE hydrology-aware edge alignment for precise flood water delineation. A feature distillation constraint further aligns fused SAR features with the optical teacher's manifold. Evaluations on SEN1FLOODS11, DEEPFLOOD, and SEN12MS demonstrate that FLoRA surpasses fusion baselines in PSNR, SSIM, and LPIPS, demonstrating that multi-modal fusion within a teacher-guided latent space yields semantically faithful and physically consistent flood-water intelligence from spaceborne observations.