Research map / 3D vision / 3D generation
SSLayout360: Semi-Supervised Indoor Layout Estimation From 360deg Panorama
Phi Vu Tran
Check 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 unlabeled-data consistency training | HorizonNet · PanoContext, 20 labels | 3D IoU (%): 61.48 ± 2.07 -> 63.05 ± 0.65 | Improved |
| Add unlabeled-data consistency training | HorizonNet · PanoContext, 963 labels | 3D IoU (%): 83.55 ± 0.31 -> 83.30 ± 0.53 | Hurt |
| Add unlabeled-data consistency training | HorizonNet · Stanford 2D-3D, 20 labels | 3D IoU (%): 62.20 ± 3.98 -> 71.60 ± 2.04 | Improved |
| Add unlabeled-data consistency training | HorizonNet · Stanford 2D-3D, 916 labels | 3D IoU (%): 82.79 ± 0.90 -> 84.66 ± 0.57 | Improved |
| Add unlabeled-data consistency training | HorizonNet · MatterportLayout (4–18 corners), 50 labels | 3D IoU (%): 63.44 ± 0.56 -> 67.42 ± 0.24 | Improved |
| Add unlabeled-data consistency training | HorizonNet · MatterportLayout (4–18 corners), 1,650 labels | 3D IoU (%): 79.12 ± 0.37 -> 80.33 ± 0.48 | Improved |
| Use EMA teacher parameters instead of shared student-teacher parameters (ablation) | SSLayout360 · PanoContext validation set | 3D IoU | Improved |
| Set consistency loss weight to λ = 1 (ablation) | SSLayout360 · PanoContext validation set | 3D IoU | Improved |
| Use a T@30% consistency-loss ramp-up (ablation) | SSLayout360 · PanoContext validation set | 3D IoU | Improved |
| Use EMA decay α = 0.999 (ablation) | SSLayout360 · PanoContext validation set | 3D IoU | Improved |
| Use squared L2 loss instead of cross-entropy for wall-wall corner predictions (ablation) | SSLayout360 · Layout estimation experiments | accuracy | Improved |
Later papers that compared with this method
1 later accepted paper reports SSLayout360* as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning (NeurIPS 2022 · better on 3 of 3 shared results)
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.
- HorizonNet — HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation (CVPR 2019) · better on 5 of 6 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
- Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image (ECCV 2020 · similarity 0.89)
- HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation (CVPR 2019 · similarity 0.89)
- GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes (ECCV 2020 · similarity 0.89)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.88)
- No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation (CVPR 2024 · similarity 0.88)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · 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.
