# SphereSR: 360deg Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation

arXiv: https://arxiv.org/abs/2112.06536 · HTML: https://mlsanity.com/paper/2112.06536/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [Meta-SR: A Magnification-Arbitrary Network for Super-Resolution](https://mlsanity.com/paper/1903.00875/) (2019)
- [Adversarial Generation of Continuous Images](https://mlsanity.com/paper/2011.12026/) (2020)
- [Image Generators with Conditionally-Independent Pixel Synthesis](https://mlsanity.com/paper/2011.13775/) (2020)
- [Learning A Single Network for Scale-Arbitrary Super-Resolution](https://mlsanity.com/paper/2004.03791/) (2020)
- [Kernel Transformer Networks for Compact Spherical Convolution](https://mlsanity.com/paper/1812.03115/) (2018)
- [Orientation-aware Semantic Segmentation on Icosahedron Spheres](https://mlsanity.com/paper/1907.12849/) (2019)
- [SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation](https://mlsanity.com/paper/2104.10325/) (2021)
- [Super-resolution of Omnidirectional Images Using Adversarial Learning](https://mlsanity.com/paper/1908.04297/) (2019)
- [A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution](https://mlsanity.com/paper/2008.10320/) (2020)

## Built on by (most cited first, 30 of 33)

- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)
- [Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2308.05493/) (2023)
- [HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions](https://mlsanity.com/paper/2303.11616/) (2023)
- [Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion](https://mlsanity.com/paper/2403.16376/) (2024)
- [OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer](https://mlsanity.com/paper/2302.03453/) (2023)
- [Polynomial Implicit Neural Representations For Large Diverse Datasets](https://mlsanity.com/paper/2303.11424/) (2023)
- [OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution](https://mlsanity.com/paper/2303.01091/) (2023)
- [Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers](https://mlsanity.com/paper/2306.12992/) (2023)
- [OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution](https://mlsanity.com/paper/2304.13471/) (2023)
- [OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution](https://mlsanity.com/paper/2308.08114/) (2023)
- [Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution](https://mlsanity.com/paper/2406.10869/) (2024)
- [Distortion-aware Transformer in 360deg Salient Object Detection](https://mlsanity.com/paper/2308.03359/) (2023)
- [Revisiting 360 Depth Estimation with PanoGabor: A New Fusion Perspective](https://mlsanity.com/paper/2408.16227/) (2024)
- [Implicit Neural Image Stitching](https://mlsanity.com/paper/2309.01409/) (2023)
- [Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding](https://mlsanity.com/paper/2503.18578/) (2025)
- [SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting](https://mlsanity.com/paper/2307.14489/) (2023)
- [Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration](https://mlsanity.com/paper/2408.09336/) (2024)
- [RealOSR: Latent Guidance Boosts Diffusion-based Real-world Omnidirectional Image Super-Resolutions](https://mlsanity.com/paper/2412.09646/) (2024)
- [SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution](https://mlsanity.com/paper/2310.00413/) (2023)
- [Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution](https://mlsanity.com/paper/2410.11506/) (2024)
- [SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction](https://mlsanity.com/paper/2602.22867/) (2026)
- [Spherical Image Inpainting with Frame Transformation and Data-driven Prior Deep Networks](https://mlsanity.com/paper/2209.14604/) (2022)
- [Non-uniform Sampling Strategies for NeRF on 360textdegree images](https://mlsanity.com/paper/2212.03635/) (2022)
- [A Comprehensive Comparison of Projections in Omnidirectional Super-Resolution](https://mlsanity.com/paper/2304.06497/) (2023)
- [WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learning](https://mlsanity.com/paper/2305.13901/) (2023)
- [Learning High-Quality Navigation and Zooming on Omnidirectional Images in Virtual Reality](https://mlsanity.com/paper/2405.00351/) (2024)
- [CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs](https://mlsanity.com/paper/2405.11564/) (2024)
- [A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution](https://mlsanity.com/paper/2506.06710/) (2025)
- [360^circ High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer](https://mlsanity.com/paper/2304.07967/) (2023)
- [CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality](https://mlsanity.com/paper/2410.05735/) (2024)

## Abstract (arXiv)

The 360degimaging has recently gained great attention; however, its angular resolution is relatively lower than that of a narrow field-of-view (FOV) perspective image as it is captured by using fisheye lenses with the same sensor size. Therefore, it is beneficial to super-resolve a 360degimage. Some attempts have been made but mostly considered the equirectangular projection (ERP) as one of the way for 360degimage representation despite of latitude-dependent distortions. In that case, as the output high-resolution(HR) image is always in the same ERP format as the low-resolution (LR) input, another information loss may occur when transforming the HR image to other projection types. In this paper, we propose SphereSR, a novel framework to generate a continuous spherical image representation from an LR 360degimage, aiming at predicting the RGB values at given spherical coordinates for super-resolution with an arbitrary 360degimage projection. Specifically, we first propose a feature extraction module that represents the spherical data based on icosahedron and efficiently extracts features on the spherical surface. We then propose a spherical local implicit image function (SLIIF) to predict RGB values at the spherical coordinates. As such, SphereSR flexibly reconstructs an HR image under an arbitrary projection type. Experiments on various benchmark datasets show that our method significantly surpasses existing methods.