PulseAugur
EN
LIVE 17:09:29

New systems generate high-fidelity 3D assets for design and fabrication

By PulseAugur Editorial · [4 sources] ·

Researchers have developed Home3D 1.0, a system capable of generating high-fidelity 3D assets for interior design and e-commerce from single images. This system comprises four modules that handle geometry reconstruction, texture prediction, material retrieval, and semantic part generation. Separately, another research effort introduces GenMF, a framework that refines generated 3D assets for monochromatic fabrication by balancing appearance preservation with structural robustness, incorporating a stress-aware regularization technique. AI

IMPACT These advancements could streamline the creation of 3D assets for design and manufacturing, potentially impacting e-commerce and physical product development.

RANK_REASON The cluster contains two distinct research papers detailing new systems and frameworks for 3D asset generation and refinement.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

New systems generate high-fidelity 3D assets for design and fabrication

COVERAGE [4]

  1. arXiv cs.AI TIER_1 English(EN) · Yiyun Fei, Guoqiu Li, Jin Song, Chuqiao Wu, Delong Wu, Hong Wu, Ziru Zeng, Haohui Chen, YinDong Kong, Jing Li, Qi Wu, Feng Zhang ·

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

    arXiv:2606.27923v1 Announce Type: cross Abstract: We present Home3D 1.0, a modular image-to-3D generation system that produces high-quality 3D assets from a single reference image, targeting interior design and e-commerce applications. Given a photograph of a furniture or decor i…

  2. arXiv cs.AI TIER_1 English(EN) · Feng Zhang ·

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

    We present Home3D 1.0, a modular image-to-3D generation system that produces high-quality 3D assets from a single reference image, targeting interior design and e-commerce applications. Given a photograph of a furniture or decor item, the system outputs a mesh with physically-bas…

  3. arXiv cs.CV TIER_1 English(EN) · Chentao Shen, Chen Jia, Mingjie Huang, Zhuang Zhang, Haisen Zhao, Xiangru Huang ·

    Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication

    arXiv:2606.26850v1 Announce Type: cross Abstract: Recent advances in 3D mesh generation have enabled the creation of visually realistic assets. However, much of their visual fidelity is encoded in textures rather than geometry. When such assets are fabricated using monochromatic …

  4. arXiv cs.CV TIER_1 English(EN) · Xiangru Huang ·

    Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication

    Recent advances in 3D mesh generation have enabled the creation of visually realistic assets. However, much of their visual fidelity is encoded in textures rather than geometry. When such assets are fabricated using monochromatic materials, texture information is largely lost, ca…

RELATED ENTITIES

RELATED TOPICS