mlsanityData to 7 Oct 2026

Interpolated SelectionConv for Spherical Images and Surfaces

arXiv 2210.10123 ↗First posted 18 Oct 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a new and general framework for convolutional neural network operations on spherical (or omnidirectional) images. Our approach represents the surface as a graph of connected points that doesn't rely on a particular sampling strategy. Additionally, by using an interpolated version of SelectionConv, we can operate on the sphere while using existing 2D CNNs and their weights. Since our method leverages existing graph implementations, it is also fast and can be fine-tuned efficiently. Our method is also general enough to be applied to any surface type, even those that are topologically non-simple. We demonstrate the effectiveness of our technique on the tasks of style transfer and segmentation for spheres as well as stylization for 3D meshes. We provide a thorough ablation study of the performance of various spherical sampling strategies.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

26 of 33 references.

References · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2018Spherical CNNscited by 452
  4. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  5. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 262
  6. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  7. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  8. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  9. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  10. 2019Spherical CNNs on Unstructured Gridscited by 76
  11. 2018MeshCNN: A Network with an Edgecited by 69
  12. 2018Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videoscited by 66
14 more
  1. 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
  2. 2018Kernel Transformer Networks for Compact Spherical Convolutioncited by 56
  3. 2019Orientation-aware Semantic Segmentation on Icosahedron Spherescited by 52
  4. 2018Learning Linear Transformations for Fast Arbitrary Style Transfercited by 48
  5. 2017Artistic style transfer for videos and spherical imagescited by 45
  6. 2020CNNs on Surfaces using Rotation-Equivariant Featurescited by 42
  7. 2018SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Imagescited by 40
  8. 2020MeshWalker: Deep Mesh Understanding by Random Walkscited by 32
  9. 2017Learning Spherical Convolution for Fast Features from 360deg Imagerycited by 22
  10. 2018Surface Networks via General Coverscited by 22
  11. 2017SalNet360: Saliency Maps for omni-directional images with CNNcited by 21
  12. 2018StyleBlit: Fast Example-Based Stylization with Local Guidancecited by 10
  13. 2022SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Datacited by 3
  14. 2017Semantic-driven Generation of Hyperlapse from 360^circ Videocited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023HEAL-SWIN: A Vision Transformer On The Spherecited by 18
  2. 2025Optimization-Free Style Transfer for 3D Gaussian Splatscited by 0