Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design

A new modular system called Home3D 1.0 can generate high-fidelity 3D assets from a single reference photograph, targeting interior design and e-commerce workflows, according to a preprint posted to the arXiv repository [1][2]. The system, described in a paper submitted on 26 June 2026, takes an image of a furniture or decor item and outputs a mesh with physically-based rendering (PBR) materials that can be decomposed into material-specific components [1][2]. The pipeline is organized into four tightly coupled modules: Geometry, Texture, Material, and Parts [2]. The Geometry module reconstructs a watertight mesh through latent SDF modelling with a geometry VAE and a coarse-to-fine flow-matching DiT, while Texture predicts multiview albedo observations, reprojects them onto the mesh, and completes unseen surface regions with a 3D texture field [2]. The Material module uses a component called MatWeaver to obtain component masks through video-based segmentation and UV-space voting, then retrieves and bakes PBR maps from a curated material library through hierarchical multi-modal matching [2]. The Parts module generates material-editable semantic part meshes with a PartVAE and PartDiT, decoding multi-head part-specific SDF fields in one pass [2]. Each module is evaluated independently with dedicated metrics, and the authors note that the results highlight both current system capability and remaining gaps toward broader deployment [2]. The paper appears on arXiv, an open-access repository of electronic preprints that are moderated but not peer-reviewed [6]. arXiv was founded in 1991 and, as of November 2024, receives about 24,000 submissions per month [6]. The repository hosts papers in fields including computer science, physics, and mathematics [6]. The Home3D 1.0 abstract page includes links to experimental community tools through the arXivLabs framework, a program that allows collaborators to develop and share new features directly on the site [1][5]. arXivLabs was formalized in 2020 to enable collaborations that share arXiv’s values of openness, community, excellence, and user data privacy [5].