Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph

Junhao Cai, Deyu Zeng, Junhao Pang, Lini Li, Zongze Wu, Xiaopin Zhong

TL;DR

This work introduces 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 and develops a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously.

Abstract

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. Our code and data are provided in the supplementary material attached in the appendix for review purposes.

ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph

TL;DR

This work introduces 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 and develops a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously.

Abstract

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. Our code and data are provided in the supplementary material attached in the appendix for review purposes.
Paper Structure (37 sections, 9 equations, 16 figures, 5 tables, 2 algorithms)

This paper contains 37 sections, 9 equations, 16 figures, 5 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Text-to-3D Generation.
  4. Domain Adaptation Challenge.
  5. Multi-View Geometric Consistency.
  6. Industrial 3D Generation Challenges.
  7. Methodology
  8. Overview
  9. Multi-Expert LoRA Ensemble Framework
  10. Teacher-Student Architecture Construction.
  11. Cross-view Hypergraph Enhanced Higher-Order Geometric Gradient Loss
  12. Hypergraph Geometric Modeling.
  13. Cross-View Geometric Consistency Through Hypergraph Neural Networks.
  14. ForgeDreamer: Unified Industrial Text-to-3D Pipeline
  15. Experiments
  16. ...and 22 more sections

Figures (16)

  • Figure 1: Overall Framework Architecture: Multi-Expert LoRA Ensemble Framework and Cross-View Hypergraph Enhancement
  • Figure 2: Overview of custom-built multi-view industrial dataset and 3D generation results. The bottom-right image presents the corresponding 3D generation result produced by our method.
  • Figure 3: Architecture of our industrial Text-to-3D generation framework - ForgeDreamer. Top: Cross-view Hypergraph Enhanced 3D Gaussian Generation pipeline with Cross-View Geometric Correlation Module (CVGCM). Bottom: Multi-Expert LoRA Ensemble Framework for cross-category industrial knowledge integration.
  • Figure 4: Qualitative Comparison with State-of-the-Art Methods. Visual results demonstrate the superior performance of our approach. See Appendix for remaining categories.
  • Figure 5: LLM-based qualitative ranking across ten object prompts, showing that our method achieves the highest overall fidelity and consistency. Full evaluation results are included in the Appendix.
  • ...and 11 more figures