ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment
Abstract
ScenePainter framework uses a hierarchical graph structure to ensure semantically consistent 3D scene generation by addressing the semantic drift problem in successive view expansion.
Perpetual 3D scene generation aims to produce long-range and coherent 3D view sequences, which is applicable for long-term video synthesis and 3D scene reconstruction. Existing methods follow a "navigate-and-imagine" fashion and rely on outpainting for successive view expansion. However, the generated view sequences suffer from semantic drift issue derived from the accumulated deviation of the outpainting module. To tackle this challenge, we propose ScenePainter, a new framework for semantically consistent 3D scene generation, which aligns the outpainter's scene-specific prior with the comprehension of the current scene. To be specific, we introduce a hierarchical graph structure dubbed SceneConceptGraph to construct relations among multi-level scene concepts, which directs the outpainter for consistent novel views and can be dynamically refined to enhance diversity. Extensive experiments demonstrate that our framework overcomes the semantic drift issue and generates more consistent and immersive 3D view sequences. Project Page: https://xiac20.github.io/ScenePainter/.
Community
We propose ScenePainter, which aims to generate semantically consistent yet visually diverse 3D view sequences starting from a single view. Project Page: https://xiac20.github.io/ScenePainter/.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration (2025)
- Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization (2025)
- CoCo4D: Comprehensive and Complex 4D Scene Generation (2025)
- Video Perception Models for 3D Scene Synthesis (2025)
- MVG4D: Image Matrix-Based Multi-View and Motion Generation for 4D Content Creation from a Single Image (2025)
- SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis (2025)
- Follow-Your-Creation: Empowering 4D Creation through Video Inpainting (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper