Research map / 3D vision / Depth and stereo
Structural Deep Metric Learning for Room Layout Estimation
Wenzhao Zheng, Jiwen Lu, Jie 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 Lmetric (structural relation loss) (ablation) | SDML · LSUN | pixel error (%): 9.93 -> 6.95 | Improved |
| add Lmetric (structural relation loss) (ablation) | SDML · LSUN | keypoint error (%): 6.42 -> 5.29 | Improved |
| add Lstr (structural prediction loss) (ablation) | SDML · LSUN | pixel error (%): 15.36 -> 6.95 | Improved |
| add Lstr (structural prediction loss) (ablation) | SDML · LSUN | keypoint error (%): 10.23 -> 5.29 | Improved |
| use Lmetric instead of dense structural loss Ldense (ablation) | SDML · LSUN | pixel error (%): 8.56 -> 6.95 | Improved |
| use Lmetric instead of dense structural loss Ldense (ablation) | SDML · LSUN | keypoint error (%): 5.86 -> 5.29 | Improved |
| add dense structural loss to RoomNet type classifier (ablation) | RoomNet · LSUN | pixel error (%): 10.46 -> 9.23 | Improved |
| add dense structural loss to RoomNet type classifier (ablation) | RoomNet · LSUN | keypoint error (%): 6.95 -> 6.27 | Improved |
| add layout decoder (replace keypoint regression) (ablation) | SDML · LSUN | pixel error (%): 9.97 -> 6.95 | Improved |
| add layout decoder (replace keypoint regression) (ablation) | SDML · LSUN | keypoint error (%): 6.60 -> 5.29 | Improved |
| replace RoomNet L2 keypoint regression with keypoint regression without decoder in SDML framework (ablation) | keypoint regression · LSUN | pixel error (%): 10.46 -> 9.97 | Improved |
| use dense structural loss instead of log-ratio dense sampling | metric model · LSUN layout retrieval (1 retrieval) | mean label distance (%): 23.3 -> 20.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DeLay — DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes (CVPR 2016) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RoomNet: End-To-End Room Layout Estimation (ICCV 2017 · similarity 0.90)
- GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes (ECCV 2020 · similarity 0.88)
- DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes (CVPR 2016 · similarity 0.87)
- PolyLayout: Multi-room Manhattan Layout Estimation (ECCV 2026 · similarity 0.87)
- Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness (CVPR 2023 · similarity 0.87)
- No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation (CVPR 2024 · 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.
