Research map / Graph learning / Knowledge and temporal graphs
DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras
Xuan Wei, Zhidan Ran, Xiaobo Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace regular conv with modulated deformable convolution (ablation) | UNet · THEODORE test | mIoU (%): 90.85 -> 91.97 | Improved |
| compute offsets and modulation scalars with a GCN in Euclidean space (ablation) | DC · THEODORE test | mIoU (%): 91.97 -> 92.57 | Improved |
| move the GCN from Euclidean space to the Poincare ball (ablation) | DC+GCN · THEODORE test | mIoU (%): 92.57 -> 92.74 | Improved |
| add geodesic distances to Poincare hyperplanes as offset parameters (ablation) | DC+GCNP · THEODORE test | mIoU (%): 92.74 -> 93.05 | Improved |
| apply DCPB at the high-level UP1 stage rather than a low-level stage (ablation) | UNet-DCPB · THEODORE test | mIoU (%): 92.69 (Up3) -> 93.05 (Up1) | Improved |
| add DCPB layers | UNet · THEODORE test | FPS: 13.8 -> 13.4 | Hurt |
| use DCPB instead of FisheyeHDK tangent-space hyperbolic deformable conv | UNet · THEODORE test | mIoU (%): 92.07 -> 93.05 | Improved |
Closest papers by meaning
- FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition (AAAI 2022 · similarity 0.88)
- From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation (ECCV 2026 · similarity 0.85)
- Spatiotemporal Deformation Perception for Fisheye Video Rectification (AAAI 2023 · similarity 0.85)
- Deformable Convolutional Networks (ICCV 2017 · similarity 0.85)
- Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption (CVPR 2024 · similarity 0.83)
- Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications (CVPR 2024 · similarity 0.82)
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.
