CVJul 25, 2025

ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment

arXiv:2507.19058v16 citationsh-index: 13
Originality Incremental advance
AI Analysis

This addresses the problem of semantic inconsistency in long-range 3D scene generation for applications like video synthesis and reconstruction, representing an incremental improvement over existing methods.

The paper tackles the semantic drift issue in perpetual 3D scene generation by proposing ScenePainter, a framework that aligns outpainting with scene comprehension using a hierarchical graph, resulting in more consistent and immersive 3D view sequences as demonstrated in experiments.

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/.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes