Research map / 3D vision / 3D generation
BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning
Changgyoon Oh, Wonjune Cho, Yujeong Chae, Daehee Park, Lin Wang, Kuk-Jin Yoon
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 bi-modal feature fusion (BFF) branch (ablation) | BIPS · Structured3D RGB-D | 2D IoU: 0.7859 -> 0.8158 | Improved |
| add bi-modal feature fusion (BFF) branch (ablation) | BIPS · Structured3D RGB-D | FAED: 381.4 -> 198.0 | Improved |
| add residual depth-aided adversarial learning (RDAL, layout/residual depth split) (ablation) | BIPS · Structured3D RGB-D | 2D IoU: 0.7164 -> 0.8158 | Improved |
| add residual depth-aided adversarial learning (RDAL, layout/residual depth split) (ablation) | BIPS · Structured3D RGB-D | FAED: 329.0 -> 198.0 | Improved |
| replace two-stage inpainting then depth synthesis (IwDS) with one-stage joint BIPS | BIPS vs CoModGAN+CSPN · Structured3D RGB-D | FAED: 640.9 -> 198.0 | Improved |
| replace two-stage inpainting then depth synthesis (IwDS) with one-stage joint BIPS | BIPS vs CoModGAN+CSPN · Structured3D RGB-D | 2D IoU: 0.7561 -> 0.8158 | Improved |
| BIPS instead of Sumantri et al. for RGB panorama | BIPS · Structured3D RGB panorama (4 inputs) | PSNR: 18.49 -> 17.29 | Hurt |
| BIPS instead of Sumantri et al. for RGB panorama | BIPS · Structured3D RGB panorama (4 inputs) | FAED: 443.4 -> 103.1 | Improved |
| BIPS instead of Sumantri et al. for RGB panorama | BIPS · Structured3D RGB panorama (4 inputs) | 2D corner error: 50.76 -> 34.68 | Improved |
| BIPS instead of CoModGAN for RGB panorama | BIPS · Structured3D RGB panorama | FAED: 208.2 -> 162.3 | Improved |
| BIPS instead of CSPN for depth panorama | BIPS · Structured3D depth panorama | FAED: 428.9 -> 131.5 | Improved |
| BIPS instead of CSPN for depth panorama | BIPS · Structured3D depth panorama | AbsREL: 0.0855 -> 0.0844 | Improved |
Closest papers by meaning
- Layout-Guided Novel View Synthesis From a Single Indoor Panorama (CVPR 2021 · similarity 0.89)
- PanoDiffusion: 360-degree Panorama Outpainting via Diffusion (ICLR 2024 · similarity 0.88)
- Indoor Panorama Planar 3D Reconstruction via Divide and Conquer (CVPR 2021 · similarity 0.87)
- Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View (ICCV 2025 · similarity 0.87)
- LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image (CVPR 2018 · similarity 0.87)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · similarity 0.85)
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.
