Research map / 3D vision / Depth and stereo
PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image
Read the paperCheck 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 |
|---|---|---|---|
| predict planes, plane-instance segmentation, and non-planar depth jointly rather than using standard per-pixel depth representation (ablation) | PlaneNet · NYUv2 entire image | Rel: 0.143 -> 0.142 | Helped |
| predict planes, plane-instance segmentation, and non-planar depth jointly rather than using standard per-pixel depth representation (ablation) | PlaneNet · NYUv2 entire image | RMSE: 0.518 -> 0.514 | Helped |
| predict planes, plane-instance segmentation, and non-planar depth jointly rather than using standard per-pixel depth representation (ablation) | PlaneNet · NYUv2 entire image | 1.25: 81.3 -> 81.2 | Hurt |
| use structured piece-wise planar depth prediction instead of a standard per-pixel depthmap | PlaneNet · NYUv2 entire image | RMSE: 0.581 -> 0.514 | Helped |
| directly infer plane parameters and instance segmentation from RGB rather than extracting planes from inferred depthmaps | PlaneNet · piece-wise planar reconstruction, inferred-depth inputs | plane segmentation recall | Helped |
| use PlaneNet's plane predictions to estimate room layout | PlaneNet · NYUv2 303 | layout error: 12.96% -> 12.64% | Helped |
Closest papers by meaning
- PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image (CVPR 2019 · similarity 0.89)
- Joint Graph-Based Depth Refinement and Normal Estimation (CVPR 2020 · similarity 0.88)
- Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding (CVPR 2019 · similarity 0.87)
- Neural 3D Scene Reconstruction With the Manhattan-World Assumption (CVPR 2022 · similarity 0.87)
- NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields (ICLR 2025 · similarity 0.86)
- DPSNet: End-to-end Deep Plane Sweep Stereo (ICLR 2019 · similarity 0.86)
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.