# HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery

arXiv: https://arxiv.org/abs/2002.06460 · HTML: https://mlsanity.com/paper/2002.06460/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2020.

## Built on by (most cited first, 30 of 42)

- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [Burst Image Restoration and Enhancement](https://mlsanity.com/paper/2110.03680/) (2021)
- [Learning Trajectory-Aware Transformer for Video Super-Resolution](https://mlsanity.com/paper/2204.04216/) (2022)
- [Open High-Resolution Satellite Imagery: The WorldStrat Dataset -- With Application to Super-Resolution](https://mlsanity.com/paper/2207.06418/) (2022)
- [Deep Reparametrization of Multi-Frame Super-Resolution and Denoising](https://mlsanity.com/paper/2108.08286/) (2021)
- [BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment](https://mlsanity.com/paper/2204.08332/) (2022)
- [Burstormer: Burst Image Restoration and Enhancement Transformer](https://mlsanity.com/paper/2304.01194/) (2023)
- [QMambaBSR: Burst Image Super-Resolution with Query State Space Model](https://mlsanity.com/paper/2408.08665/) (2024)
- [Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts](https://mlsanity.com/paper/2104.06191/) (2021)
- [Can SAM Boost Video Super-Resolution?](https://mlsanity.com/paper/2305.06524/) (2023)
- [Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation](https://mlsanity.com/paper/2111.03231/) (2021)
- [High-Resolution Building and Road Detection from Sentinel-2](https://mlsanity.com/paper/2310.11622/) (2023)
- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [MuS2: A Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution](https://mlsanity.com/paper/2210.02745/) (2022)
- [Deep Learning for Satellite Image Time Series Analysis: A Review](https://mlsanity.com/paper/2404.03936/) (2024)
- [Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement](https://mlsanity.com/paper/2304.06703/) (2023)
- [Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images](https://mlsanity.com/paper/2301.11154/) (2023)
- [Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites](https://mlsanity.com/paper/2205.02031/) (2022)
- [Contrastive Learning for Climate Model Bias Correction and Super-Resolution](https://mlsanity.com/paper/2211.07555/) (2022)
- [Cross-sensor super-resolution of irregularly sampled Sentinel-2 time series](https://mlsanity.com/paper/2404.16409/) (2024)
- [Kernel-aware Burst Blind Super-Resolution](https://mlsanity.com/paper/2112.07315/) (2021)
- [RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution](https://mlsanity.com/paper/2306.17595/) (2023)
- [L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagery](https://mlsanity.com/paper/2304.06871/) (2023)
- [Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensing](https://mlsanity.com/paper/2311.18082/) (2023)
- [Proba-V-ref: Repurposing the Proba-V challenge for reference-aware super resolution](https://mlsanity.com/paper/2101.10200/) (2021)
- [Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution](https://mlsanity.com/paper/2312.07823/) (2023)
- [Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using Airborne LiDAR HD Reference Data across Metropolitan France](https://mlsanity.com/paper/2512.11524/) (2025)
- [RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network](https://mlsanity.com/paper/2110.13217/) (2021)
- [Multi-temporal speckle reduction with self-supervised deep neural networks](https://mlsanity.com/paper/2207.11095/) (2022)
- [IQUAFLOW: A new framework to measure image quality](https://mlsanity.com/paper/2210.13269/) (2022)

## Abstract (arXiv)

Generative deep learning has sparked a new wave of Super-Resolution (SR) algorithms that enhance single images with impressive aesthetic results, albeit with imaginary details. Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views. This is important for satellite monitoring of human impact on the planet -- from deforestation, to human rights violations -- that depend on reliable imagery. To this end, we present HighRes-net, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion: (i) co-registration, (ii) fusion, (iii) up-sampling, and (iv) registration-at-the-loss. Co-registration of low-resolution views is learned implicitly through a reference-frame channel, with no explicit registration mechanism. We learn a global fusion operator that is applied recursively on an arbitrary number of low-resolution pairs. We introduce a registered loss, by learning to align the SR output to a ground-truth through ShiftNet. We show that by learning deep representations of multiple views, we can super-resolve low-resolution signals and enhance Earth Observation data at scale. Our approach recently topped the European Space Agency's MFSR competition on real-world satellite imagery.