RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting

TL;DR

RoomTex is a novel iterative inpainting framework that generates high-fidelity, style-consistent textures for indoor scenes by unwrapping scene meshes, creating panoramic references, and refining object textures from multiple views.

Contribution

The paper introduces RoomTex, a coarse-to-fine 3D scene texturing method that ensures global consistency and allows interactive, fine-grained texture editing for compositional indoor scenes.

Findings

Capable of generating high-quality, diverse room textures.

Supports interactive fine-grained texture control.

Enables flexible scene editing with compositional meshes.

Abstract

The advancement of diffusion models has pushed the boundary of text-to-3D object generation. While it is straightforward to composite objects into a scene with reasonable geometry, it is nontrivial to texture such a scene perfectly due to style inconsistency and occlusions between objects. To tackle these problems, we propose a coarse-to-fine 3D scene texturing framework, referred to as RoomTex, to generate high-fidelity and style-consistent textures for untextured compositional scene meshes. In the coarse stage, RoomTex first unwraps the scene mesh to a panoramic depth map and leverages ControlNet to generate a room panorama, which is regarded as the coarse reference to ensure the global texture consistency. In the fine stage, based on the panoramic image and perspective depth maps, RoomTex will refine and texture every single object in the room iteratively along a series of selected camera views, until this object is completely painted. Moreover, we propose to maintain superior alignment between RGB and depth spaces via subtle edge detection methods. Extensive experiments show our method is capable of generating high-quality and diverse room textures, and more importantly, supporting interactive fine-grained texture control and flexible scene editing thanks to our inpainting-based framework and compositional mesh input. Our project page is available at https://qwang666.github.io/RoomTex/.