RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing

TL;DR

RoomPainter introduces a novel zero-shot, view-integrated diffusion framework for indoor scene texturing that ensures high-fidelity, globally and locally consistent textures efficiently, surpassing existing methods in quality and coherence.

Contribution

The paper presents RoomPainter, a zero-shot diffusion-based framework with a two-stage strategy and attention-guided multi-view sampling for consistent indoor scene texturing.

Findings

Achieves high visual quality and global consistency in indoor scene texturing.

Enhances local consistency and occlusion handling through a two-stage sampling process.

Demonstrates superior efficiency compared to optimization-based approaches.

Abstract

Indoor scene texture synthesis has garnered significant interest due to its important potential applications in virtual reality, digital media and creative arts. Existing diffusion-model-based researches either rely on per-view inpainting techniques, which are plagued by severe cross-view inconsistencies and conspicuous seams, or adopt optimization-based approaches that involve substantial computational overhead. In this work, we present RoomPainter, a framework that seamlessly integrates efficiency and consistency to achieve high-fidelity texturing of indoor scenes. The core of RoomPainter features a zero-shot technique that effectively adapts a 2D diffusion model for 3D-consistent texture synthesis, along with a two-stage generation strategy that ensures both global and local consistency. Specifically, we introduce Attention-Guided Multi-View Integrated Sampling (MVIS) combined with a neighbor-integrated attention mechanism for zero-shot texture map generation. Using the MVIS, we firstly generate texture map for the entire room to ensure global consistency, then adopt its variant, namely Attention-Guided Multi-View Integrated Repaint Sampling (MVRS) to repaint individual instances within the room, thereby further enhancing local consistency and addressing the occlusion problem. Experiments demonstrate that RoomPainter achieves superior performance for indoor scene texture synthesis in visual quality, global consistency and generation efficiency.