Prim2Room: Layout-Controllable Room Mesh Generation from Primitives

TL;DR

Prim2Room is a controllable 3D room mesh generation framework that uses 2D layouts and 3D primitives, enabling precise customization and improved alignment of furniture and room structures.

Contribution

It introduces an adaptive viewpoint selection and non-rigid depth registration to enhance control, diversity, and accuracy in 3D room scene generation.

Findings

Improved alignment between generated objects and primitives.

Enhanced control over room layout customization.

Higher aesthetic quality of generated 3D scenes.

Abstract

We propose Prim2Room, a novel framework for controllable room mesh generation leveraging 2D layout conditions and 3D primitive retrieval to facilitate precise 3D layout specification. Diverging from existing methods that lack control and precision, our approach allows for detailed customization of room-scale environments. To overcome the limitations of previous methods, we introduce an adaptive viewpoint selection algorithm that allows the system to generate the furniture texture and geometry from more favorable views than predefined camera trajectories. Additionally, we employ non-rigid depth registration to ensure alignment between generated objects and their corresponding primitive while allowing for shape variations to maintain diversity. Our method not only enhances the accuracy and aesthetic appeal of generated 3D scenes but also provides a user-friendly platform for detailed room design.