Research map / 3D vision / 3D generation
RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models
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 |
|---|---|---|---|
| Use incremental RGBD view inpainting with mesh rendering and fusion instead of the compared scene-synthesis methods | ScanNet-V2 scene synthesis · ScanNet-V2, 5% views | CD_mesh: 2363 -> 1058 | Helped |
| Use incremental RGBD view inpainting with mesh rendering and fusion instead of the compared scene-synthesis methods | ScanNet-V2 scene synthesis · ScanNet-V2, 50% views | PSNR_color: 20.9 -> 18.4 | Hurt |
| Add conditioning on the rendered known RGBD region (ablation) | RGBD2 · ScanNet-V2, 5% views | PSNR_color: 12.4 -> 14.6 | Helped |
| Add conditioning on the rendered known RGBD region (ablation) | RGBD2 · ScanNet-V2, 5% views | MSE_depth: 1.001 -> 0.897 | Helped |
| Add RGBD inpainting (ablation) | Conditioned RGBD2 · ScanNet-V2, 5% views | PSNR_color: 12.5 -> 14.6 | Helped |
| Add RGBD inpainting (ablation) | Conditioned RGBD2 · ScanNet-V2, 5% views | MSE_depth: 0.897 -> 0.825 | Helped |
| Increase guidance factor from β=1.0 to β=2.0 (ablation) | RGBD2 · ScanNet-V2, 5% views | PSNR_color: 14.6 -> 14.5 | No clear effect |
| Increase guidance factor from β=1.0 to β=5.0 (ablation) | RGBD2 · ScanNet-V2, 5% views | PSNR_color: 14.6 -> 13.3 | Hurt |
| Increase guidance factor from β=1.0 to β=5.0 (ablation) | RGBD2 · ScanNet-V2, 50% views | MSE_depth: 0.628 -> 0.582 | Helped |
| Increase guidance factor from β=1.0 to β=5.0 (ablation) | RGBD2 · ScanNet-V2, 50% views | PSNR_color: 18.4 -> 18.2 | Hurt |
Closest papers by meaning
- Coherent 3D Scene Diffusion From a Single RGB Image (NeurIPS 2024 · similarity 0.89)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.89)
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation (CVPR 2024 · similarity 0.88)
- RAD: Region-Aware Diffusion Models for Image Inpainting (CVPR 2025 · similarity 0.88)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.87)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · 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.