Temporal-Spatial Tubelet Embedding for Cloud-Robust MSI Reconstruction using MSI-SAR Fusion: A Multi-Head Self-Attention Video Vision Transformer Approach

TL;DR

This paper introduces a novel Video Vision Transformer framework with temporal-spatial fusion embedding for improved multispectral imagery reconstruction in cloud-covered regions, leveraging tubelet extraction and multi-modal fusion.

Contribution

It proposes a temporal-spatial fusion embedding using tubelets in a ViViT-based framework, reducing information loss and enhancing reconstruction accuracy in MSI data affected by clouds.

Findings

Achieved 2.23% lower MSE on MSI reconstruction compared to baseline.

Realized 10.33% improvement with SAR-MSI fusion over non-fused methods.

Demonstrated robustness in cloud-affected agricultural monitoring scenarios.

Abstract

Cloud cover in multispectral imagery (MSI) significantly hinders early-season crop mapping by corrupting spectral information. Existing Vision Transformer(ViT)-based time-series reconstruction methods, like SMTS-ViT, often employ coarse temporal embeddings that aggregate entire sequences, causing substantial information loss and reducing reconstruction accuracy. To address these limitations, a Video Vision Transformer (ViViT)-based framework with temporal-spatial fusion embedding for MSI reconstruction in cloud-covered regions is proposed in this study. Non-overlapping tubelets are extracted via 3D convolution with constrained temporal span $(t=2)$, ensuring local temporal coherence while reducing cross-day information degradation. Both MSI-only and SAR-MSI fusion scenarios are considered during the experiments. Comprehensive experiments on 2020 Traill County data demonstrate notable performance improvements: MTS-ViViT achieves a 2.23\% reduction in MSE compared to the MTS-ViT baseline, while SMTS-ViViT achieves a 10.33\% improvement with SAR integration over the SMTS-ViT baseline. The proposed framework effectively enhances spectral reconstruction quality for robust agricultural monitoring.