Saved in:
Bibliographic Details
Main Authors: Cai, Junhao, Zeng, Deyu, Pang, Junhao, Li, Lini, Wu, Zongze, Zhong, Xiaopin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09266
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908929868431360
author Cai, Junhao
Zeng, Deyu
Pang, Junhao
Li, Lini
Wu, Zongze
Zhong, Xiaopin
author_facet Cai, Junhao
Zeng, Deyu
Pang, Junhao
Li, Lini
Wu, Zongze
Zhong, Xiaopin
contents Current text-to-3D generation methods excel in natural scenes but struggle with industrial applications due to two critical limitations: domain adaptation challenges where conventional LoRA fusion causes knowledge interference across categories, and geometric reasoning deficiencies where pairwise consistency constraints fail to capture higher-order structural dependencies essential for precision manufacturing. We propose a novel framework named ForgeDreamer addressing both challenges through two key innovations. First, we introduce a Multi-Expert LoRA Ensemble mechanism that consolidates multiple category-specific LoRA models into a unified representation, achieving superior cross-category generalization while eliminating knowledge interference. Second, building on enhanced semantic understanding, we develop a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously. These components work synergistically improved semantic understanding, enables more effective geometric reasoning, while hypergraph modeling ensures manufacturing-level consistency. Extensive experiments on a custom industrial dataset demonstrate superior semantic generalization and enhanced geometric fidelity compared to state-of-the-art approaches. Code is available at https://github.com/Junhaocai27/ForgeDreamer
format Preprint
id arxiv_https___arxiv_org_abs_2603_09266
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph
Cai, Junhao
Zeng, Deyu
Pang, Junhao
Li, Lini
Wu, Zongze
Zhong, Xiaopin
Computer Vision and Pattern Recognition
Current text-to-3D generation methods excel in natural scenes but struggle with industrial applications due to two critical limitations: domain adaptation challenges where conventional LoRA fusion causes knowledge interference across categories, and geometric reasoning deficiencies where pairwise consistency constraints fail to capture higher-order structural dependencies essential for precision manufacturing. We propose a novel framework named ForgeDreamer addressing both challenges through two key innovations. First, we introduce a Multi-Expert LoRA Ensemble mechanism that consolidates multiple category-specific LoRA models into a unified representation, achieving superior cross-category generalization while eliminating knowledge interference. Second, building on enhanced semantic understanding, we develop a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously. These components work synergistically improved semantic understanding, enables more effective geometric reasoning, while hypergraph modeling ensures manufacturing-level consistency. Extensive experiments on a custom industrial dataset demonstrate superior semantic generalization and enhanced geometric fidelity compared to state-of-the-art approaches. Code is available at https://github.com/Junhaocai27/ForgeDreamer
title ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.09266