# OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution

arXiv: https://arxiv.org/abs/2308.08114 · HTML: https://mlsanity.com/paper/2308.08114/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 16 Aug 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [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)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Meta-SR: A Magnification-Arbitrary Network for Super-Resolution](https://mlsanity.com/paper/1903.00875/) (2019)
- [Tangent Images for Mitigating Spherical Distortion](https://mlsanity.com/paper/1912.09390/) (2019)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [SphereSR: 360deg Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation](https://mlsanity.com/paper/2112.06536/) (2021)
- [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)
- [Learning Local Implicit Fourier Representation for Image Warping](https://mlsanity.com/paper/2207.01831/) (2022)
- [M"obius Convolutions for Spherical CNNs](https://mlsanity.com/paper/2201.12212/) (2022)
- [Data augmentation with Mobius transformations](https://mlsanity.com/paper/2002.02917/) (2020)
- [3D Human Pose Estimation Using M"obius Graph Convolutional Networks](https://mlsanity.com/paper/2203.10554/) (2022)
- [View-aware Salient Object Detection for 360deg Omnidirectional Image](https://mlsanity.com/paper/2209.13222/) (2022)
- [Squares that Look Round: Transforming Spherical Images](https://mlsanity.com/paper/1605.01396/) (2016)
- [Real-time correction of panoramic images using hyperbolic M"obius transformations](https://mlsanity.com/paper/1504.04565/) (2015)

## Built on by (most cited first, 7 of 7)

- [Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion](https://mlsanity.com/paper/2403.16376/) (2024)
- [A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision](https://mlsanity.com/paper/2502.10444/) (2025)
- [PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation](https://mlsanity.com/paper/2406.13378/) (2024)
- [ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images](https://mlsanity.com/paper/2404.16825/) (2024)
- [M"obius Transform for Mitigating Perspective Distortions in Representation Learning](https://mlsanity.com/paper/2405.02296/) (2024)
- [Learning High-Quality Navigation and Zooming on Omnidirectional Images in Virtual Reality](https://mlsanity.com/paper/2405.00351/) (2024)
- [Shear-Free Viewport Magnification for 360-Degree via Spherical Mobius Boosts](https://mlsanity.com/paper/2606.20684/) (2026)

## Abstract (arXiv)

Omnidirectional images (ODIs) have become increasingly popular, as their large field-of-view (FoV) can offer viewers the chance to freely choose the view directions in immersive environments such as virtual reality. The M"obius transformation is typically employed to further provide the opportunity for movement and zoom on ODIs, but applying it to the image level often results in blurry effect and aliasing problem. In this paper, we propose a novel deep learning-based approach, called OmniZoomer, to incorporate the M"obius transformation into the network for movement and zoom on ODIs. By learning various transformed feature maps under different conditions, the network is enhanced to handle the increasing edge curvatures, which alleviates the blurry effect. Moreover, to address the aliasing problem, we propose two key components. Firstly, to compensate for the lack of pixels for describing curves, we enhance the feature maps in the high-resolution (HR) space and calculate the transformed index map with a spatial index generation module. Secondly, considering that ODIs are inherently represented in the spherical space, we propose a spherical resampling module that combines the index map and HR feature maps to transform the feature maps for better spherical correlation. The transformed feature maps are decoded to output a zoomed ODI. Experiments show that our method can produce HR and high-quality ODIs with the flexibility to move and zoom in to the object of interest. Project page is available at http://vlislab22.github.io/OmniZoomer/.