Research map / 3D vision / 3D generation
Automatic 3D Indoor Scene Modeling From Single Panorama
Yang Yang, Shi Jin, Ruiyang Liu, Sing Bing Kang, Jingyi Yu
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 |
|---|---|---|---|
| Use the proposed panorama reconstruction method instead of Yang et al. [30] | Indoor panorama depth reconstruction · FARO background | depth cosine distance (×10−2): 6.10 -> 5.59 | Improved |
| Use the proposed panorama reconstruction method instead of Yang et al. [30] | Indoor panorama depth reconstruction · Synthetic background | depth cosine distance (×10−2): 7.56 -> 3.12 | Improved |
| Use the proposed panorama reconstruction method instead of Chen et al. [4] | Indoor panorama depth reconstruction · FARO background | depth cosine distance (×10−2): 8.51 -> 5.59 | Improved |
| Use the proposed panorama reconstruction method instead of Chen et al. [4] | Indoor panorama depth reconstruction · Synthetic background | depth cosine distance (×10−2): 10.01 -> 3.12 | Improved |
| Use the proposed panorama reconstruction method instead of Yang et al. [30] | Indoor panorama depth reconstruction · FARO object region | depth cosine distance (×10−2): 2.94 -> 2.43 | Improved |
| Use the proposed panorama reconstruction method instead of Yang et al. [30] | Indoor panorama depth reconstruction · Synthetic object region | depth cosine distance (×10−2): 3.53 -> 3.27 | Improved |
| Use the proposed panorama reconstruction method instead of Chen et al. [4] | Indoor panorama depth reconstruction · FARO object region | depth cosine distance (×10−2): 7.62 -> 2.43 | Improved |
| Use the proposed panorama reconstruction method instead of Chen et al. [4] | Indoor panorama depth reconstruction · Synthetic object region | depth cosine distance (×10−2): 16.33 -> 3.27 | Improved |
| Add surface normal information (ablation) | Proposed panorama reconstruction method · FARO and synthetic datasets | cosine (×10−2): 5.30 -> 5.12 | Improved |
| Add surface normal information (ablation) | Proposed panorama reconstruction method · FARO and synthetic datasets | L2: 0.18 -> 0.16 | Improved |
| Add semantic cues (ablation) | Proposed panorama reconstruction method · FARO and synthetic datasets | cosine (×10−2): 5.48 -> 5.12 | Improved |
| Add semantic cues (ablation) | Proposed panorama reconstruction method · FARO and synthetic datasets | L2: 0.19 -> 0.16 | Improved |
Closest papers by meaning
- Efficient 3D Room Shape Recovery From a Single Panorama (CVPR 2016 · similarity 0.92)
- Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image (CVPR 2020 · similarity 0.91)
- LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image (CVPR 2018 · similarity 0.89)
- GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes (ECCV 2020 · similarity 0.89)
- Layout-Guided Novel View Synthesis From a Single Indoor Panorama (CVPR 2021 · similarity 0.88)
- Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion (CVPR 2024 · similarity 0.88)
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.
