# SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images

arXiv: https://arxiv.org/abs/1811.08196 · HTML: https://mlsanity.com/paper/1811.08196/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 30 of 41)

- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation](https://mlsanity.com/paper/2203.01452/) (2022)
- [360MonoDepth: High-Resolution 360deg Monocular Depth Estimation](https://mlsanity.com/paper/2111.15669/) (2021)
- [Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2207.11860/) (2022)
- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [Guided Co-Modulated GAN for 360deg Field of View Extrapolation](https://mlsanity.com/paper/2204.07286/) (2022)
- [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)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [PanoSwin: a Pano-style Swin Transformer for Panorama Understanding](https://mlsanity.com/paper/2308.14726/) (2023)
- [PanelNet: Understanding 360 Indoor Environment via Panel Representation](https://mlsanity.com/paper/2305.09078/) (2023)
- [Single Frame Semantic Segmentation Using Multi-Modal Spherical Images](https://mlsanity.com/paper/2308.09369/) (2023)
- [Panoramic Vision Transformer for Saliency Detection in 360deg Videos](https://mlsanity.com/paper/2209.08956/) (2022)
- [Learning Local Implicit Fourier Representation for Image Warping](https://mlsanity.com/paper/2207.01831/) (2022)
- [Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360deg Omnidirectional Image](https://mlsanity.com/paper/2212.12378/) (2022)
- [SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception](https://mlsanity.com/paper/2412.06968/) (2024)
- [Spherical Transformer](https://mlsanity.com/paper/2202.04942/) (2022)
- [3D Scene Geometry Estimation from 360^circ Imagery: A Survey](https://mlsanity.com/paper/2401.09252/) (2024)
- [SGFormer: Spherical Geometry Transformer for 360 Depth Estimation](https://mlsanity.com/paper/2404.14979/) (2024)
- [OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression](https://mlsanity.com/paper/2107.09179/) (2021)
- [360deg Optical Flow using Tangent Images](https://mlsanity.com/paper/2112.14331/) (2021)
- [SphereDepth: Panorama Depth Estimation from Spherical Domain](https://mlsanity.com/paper/2208.13714/) (2022)
- [Unbiased IoU for Spherical Image Object Detection](https://mlsanity.com/paper/2108.08029/) (2021)
- [Distortion-aware Transformer in 360deg Salient Object Detection](https://mlsanity.com/paper/2308.03359/) (2023)
- [Estimating Depth of Monocular Panoramic Image with Teacher-Student Model Fusing Equirectangular and Spherical Representations](https://mlsanity.com/paper/2405.16858/) (2024)
- [Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration](https://mlsanity.com/paper/2408.09336/) (2024)
- [Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors](https://mlsanity.com/paper/2502.05902/) (2025)
- [Interpolated SelectionConv for Spherical Images and Surfaces](https://mlsanity.com/paper/2210.10123/) (2022)
- [See360: Novel Panoramic View Interpolation](https://mlsanity.com/paper/2401.03431/) (2024)
- [PanoMixSwap Panorama Mixing via Structural Swapping for Indoor Scene Understanding](https://mlsanity.com/paper/2309.09514/) (2023)

## Abstract (arXiv)

Omni-directional cameras have many advantages overconventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have beenproposed recently to apply convolutional neural networks(CNNs) to omni-directional images for various visual tasks.However, most of them use image representations defined inthe Euclidean space after transforming the omni-directionalviews originally formed in the non-Euclidean space. Thistransformation leads to shape distortion due to nonuniformspatial resolving power and the loss of continuity. Theseeffects make existing convolution kernels experience diffi-culties in extracting meaningful information.This paper presents a novel method to resolve such prob-lems of applying CNNs to omni-directional images. Theproposed method utilizes a spherical polyhedron to rep-resent omni-directional views. This method minimizes thevariance of the spatial resolving power on the sphere sur-face, and includes new convolution and pooling methodsfor the proposed representation. The proposed method canalso be adopted by any existing CNN-based methods. Thefeasibility of the proposed method is demonstrated throughclassification, detection, and semantic segmentation taskswith synthetic and real datasets.