Research map / 3D vision / 3D generation
ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment
Chong Xia, Shengjun Zhang, Fangfu Liu, Chang Liu, Khodchaphun Hirunyaratsameewong, Yueqi Duan
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 reconstruction loss (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.523 -> 0.924 | Improved |
| add prior preservation loss (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.894 -> 0.924 | Improved |
| add cross-attention loss (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.723 -> 0.924 | Improved |
| add first-level environment node (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.774 -> 0.924 | Improved |
| add third-level object nodes (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.857 -> 0.924 | Improved |
| add relation edges to the graph (ablation) | ScenePainter · Scene fidelity ablation | DINO: 0.634 -> 0.924 | Improved |
| add relation edges to the graph (ablation) | ScenePainter · Scene fidelity ablation | CLIP-I: 0.672 -> 0.949 | Improved |
| replace Break-A-Scene customization with SceneConceptGraph scene-level customization | ScenePainter · Scene fidelity (single image customization, 30 scenes) | DINO: 0.877 -> 0.931 | Improved |
| replace WonderJourney outpainting with scene-prior-aligned outpainter | WonderJourney · 3D view generation user study | consistency preference: 92.6% | Improved |
Closest papers by meaning
- 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation (CVPR 2024 · similarity 0.89)
- SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation (CVPR 2025 · similarity 0.88)
- Disentangled 3D Scene Generation with Layout Learning (ICML 2024 · similarity 0.87)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.87)
- Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation (NeurIPS 2024 · similarity 0.86)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.86)
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.
