Research map / 3D vision / Face and shape
Recovering 3D Planes from a Single Image via Convolutional Neural Networks
Fengting Yang, Zihan Zhou
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 |
|---|---|---|---|
| add plane structure-induced loss network instead of depth prediction plus J-Linkage | plane recovery CNN · SYNTHIA | Rand index (RI): 0.825 -> 0.925 | Improved |
| replace Geometric Context with the CNN | plane recovery CNN · SYNTHIA | segmentation covering (SC): 0.636 -> 0.797 | Improved |
| fine-tune the SYNTHIA-trained network on Cityscapes (ablation) | plane recovery CNN · Cityscapes | Rand index (RI): 0.759 -> 0.884 | Improved |
| fine-tune on Cityscapes (ablation) | plane recovery CNN · Cityscapes | variation of information (VOI): 1.834 -> 1.239 | Improved |
| fine-tune on Cityscapes (ablation) | plane recovery CNN · Cityscapes | segmentation covering (SC): 0.597 -> 0.769 | Improved |
| no fine-tuning: apply SYNTHIA-trained model directly versus Depth+J-Linkage | plane recovery CNN · Cityscapes | Rand index (RI): 0.713 -> 0.759 | Improved |
| derive depth from predicted planes instead of a direct depth network (DispNet) | plane recovery CNN · SYNTHIA | Abs Rel: 0.0451 -> 0.0431 | Improved |
| derive depth from predicted planes instead of a direct depth network (DispNet) | plane recovery CNN · SYNTHIA | RMSE: 1.6491 -> 2.2405 | Hurt |
| derive depth from predicted planes instead of a direct depth network (DispNet) | plane recovery CNN · Cityscapes | Abs Rel: 0.0855 -> 0.1042 | Hurt |
Closest papers by meaning
- PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image (CVPR 2019 · similarity 0.90)
- NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields (ICLR 2025 · similarity 0.89)
- PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image (CVPR 2018 · similarity 0.89)
- PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View (ICCV 2023 · similarity 0.89)
- Towards In-the-wild 3D Plane Reconstruction from a Single Image (CVPR 2025 · similarity 0.88)
- AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings (CVPR 2024 · similarity 0.87)
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.
