Abstract
Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented, lacking publicly available pretrained models and misaligned with advances in compression for natural imagery. Image codecs overlook temporal redundancy, while video codecs rely on motion priors that fail to capture the radiometric evolution of largely static scenes. We introduce TerraCodec (TEC), a family of learned codecs tailored to EO. TEC includes efficient image-based variants adapted to multispectral inputs, as well as a Temporal Transformer model (TEC-TT) that leverages dependencies across time. To overcome the fixed-rate setting of today's neural codecs, we present Latent Repacking, a novel method for training flexible-rate transformer models that operate on varying rate-distortion settings. Trained on Sentinel-2 data, TerraCodec outperforms classical codecs, achieving 3-10x stronger compression at equivalent image quality. Beyond compression, TEC-TT enables zero-shot cloud inpainting, surpassing state-of-the-art methods on the AllClear benchmark. Our results establish bespoke, learned compression algorithms as a promising direction for Earth observation. Code and model weights will be released under a permissive license.
Abstract (translated)
地球观测（EO）卫星产生了大量的多光谱图像时间序列，这对存储和传输提出了紧迫的挑战。然而，目前的EO压缩方法仍然比较分散，缺乏公开可用的预训练模型，并且与自然影像压缩技术的进步不一致。传统的图象编解码器忽略了时间冗余，而视频编解码器依赖于运动先验信息，这些信息无法捕捉到静止场景中辐射量的变化。 我们引入了TerraCodec（TEC），这是一个专为EO设计的学习编码器家族。TEC包括针对多光谱输入进行了优化的高效图像变体，以及利用时间依赖性的时序变换模型（TEC-TT）。为了克服现有神经编解码器固定率设置的问题，我们提出了一种称为潜在重组的新方法，该方法用于训练在不同率失真设置下运行的灵活率转换模型。在Sentinel-2数据集上进行训练后，TerraCodec在等效图像质量的情况下，比传统的编解码器实现了3到10倍更强的压缩效果。 除了压缩性能外，TEC-TT还能够在无监督条件下实现云层插补，并且在AllClear基准测试中超越了现有最先进的方法。我们的研究结果表明，为地球观测量身定制的学习压缩算法是一个很有前途的研究方向。代码和模型权重将以宽松许可协议的形式发布。
URL
https://arxiv.org/abs/2510.12670
