Research map / Detection and segmentation / CNN features
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SpherePHD instead of ERP | the CNN representation · MNIST | accuracy (%): 75.51 -> 88.13 | Helped |
| Use SpherePHD instead of cube padding | the CNN representation · MNIST | accuracy (%): 74.56 -> 88.13 | Helped |
| Use SpherePHD instead of ERP | the vehicle detector · SYNTHIA | AP (%): 56.04 -> 43.00 | Hurt |
| Use SpherePHD instead of ERP | the vehicle detector · SYNTHIA (rotation-augmented) | AP (%): 39.87 -> 64.52 | Helped |
| Use SpherePHD instead of cube map | the vehicle detector · SYNTHIA | AP (%): 30.13 -> 43.00 | Helped |
| Use SpherePHD instead of cube map | the vehicle detector · SYNTHIA (rotation-augmented) | AP (%): 26.03 -> 64.52 | Helped |
| Use SpherePHD instead of ERP | the semantic segmentation network · SYNTHIA | per-class accuracy (%): 62.69 -> 70.08 | Helped |
| Use SpherePHD instead of ERP | the semantic segmentation network · Stanford2D3D | overall pixel accuracy (%): 35.02 -> 51.40 | Helped |
Closest papers by meaning
- Learning Spherical Convolution for Fast Features from 360° Imagery (NeurIPS 2017 · similarity 0.88)
- Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera (CVPR 2026 · similarity 0.88)
- Geometry Aware Convolutional Filters for Omnidirectional Images Representation (ICML 2019 · similarity 0.88)
- SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception (CVPR 2025 · similarity 0.87)
- Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation (ICLR 2025 · similarity 0.86)
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.