Research map / 3D vision / 3D generation
Learning Object Context for Novel-View Scene Layout Generation
Check 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 |
|---|---|---|---|
| Add the Object Context Transformation (OCT) module (ablation) | Novel-view scene layout generation model · RealEstate10K | NLL: 1.71 -> 1.53 | Helped |
| Add the Object Context Transformation (OCT) module (ablation) | Novel-view scene layout generation model · RealEstate10K | FID: 109 -> 85 | Helped |
| Add camera transformation to the OCT module (ablation) | Novel-view scene layout generation model · RealEstate10K | NLL: 1.65 -> 1.53 | Helped |
| Add camera transformation to the OCT module (ablation) | Novel-view scene layout generation model · RealEstate10K | VSC: 0.089 -> 0.059 | Helped |
| Add OrderNet for object occlusion ordering (ablation) | Novel-view scene layout generation model · RealEstate10K | VSC: 0.082 -> 0.059 | Helped |
| Add refinement blocks (ablation) | Novel-view scene layout generation model · RealEstate10K | FID: 93 -> 85 | Helped |
| Add adversarial loss (ablation) | Novel-view scene layout generation model · RealEstate10K | FID: 91 -> 85 | Helped |
| Add OLC to LayoutGAN | LayoutGAN · RealEstate10K | NLL: 2.05 -> 1.96 | Helped |
| Use object-context modeling rather than the GVSNet baseline | Novel-view scene layout generation · RealEstate10K | NLL: 1.69 -> 1.53 | Helped |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- Disentangled 3D Scene Generation with Layout Learning (ICML 2024 · similarity 0.88)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.88)
- MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes (CVPR 2025 · similarity 0.88)
- From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries (NeurIPS 2025 · similarity 0.88)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (AAAI 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.