Haiwen Huang

Haiwen Huang

Auto-generated profile, based on publicly available information

Haiwen Huang

East China Normal University, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

2 December 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
NXNan Xiang
Nan Xiang
TLTianyi Liang
Tianyi Liang
HHHaiwen Huang
Haiwen Huang
SJShiqi Jiang
Shiqi Jiang
HHHao Huang
Hao Huang
CLChenhui Li
Chenhui Li
Text-to-3D (T23D) generation has transformed digital content creation, yet remains bottlenecked by blind trial-and-error prompting processes that yield unpredictable results. While visual prompt engineering has advanced in text-to-image domains, its application to 3D generation presents unique challenges requiring multi-view consistency evaluation and spatial understanding. We present Sel3DCraft, a visual prompt engineering system for T23D that transforms unstructured exploration into a guided visual process. Our approach introduces three key innovations: a dual-branch structure combining retrieval and generation for diverse candidate exploration; a multi-view hybrid scoring approach that leverages MLLMs with innovative high-level metrics to assess 3D models with human-expert consistency; and a prompt-driven visual analytics suite that enables intuitive defect identification and refinement. Extensive testing and a user study demonstrate that Sel3DCraft surpasses other T23D systems in supporting creativity for designers.

21 May 2025 in Computer Graphics Forum
Verified
Journal Article
Closed access
HHHaiwen Huang
Haiwen Huang
JCJuntong Chen
Juntong Chen
CWChangbo Wang
Changbo Wang
CLChenhui Li
Chenhui Li

1 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
NXNan Xiang
Nan Xiang
TLTianyi Liang
Tianyi Liang
HHHaiwen Huang
Haiwen Huang
SJShiqi Jiang
Shiqi Jiang
HHHao Huang
Hao Huang
CLChenhui Li
Chenhui Li
Text-to-3D (T23D) generation has transformed digital content creation, yet remains bottlenecked by blind trial-and-error prompting processes that yield unpredictable results. While visual prompt engineering has advanced in text-to-image domains, its application to 3D generation presents unique challenges requiring multi-view consistency evaluation and spatial understanding. We present Sel3DCraft, a visual prompt engineering system for T23D that transforms unstructured exploration into a guided visual process. Our approach introduces three key innovations: a dual-branch structure combining retrieval and generation for diverse candidate exploration; a multi-view hybrid scoring approach that leverages MLLMs with innovative high-level metrics to assess 3D models with human-expert consistency; and a prompt-driven visual analytics suite that enables intuitive defect identification and refinement. Extensive testing and user studies demonstrate that Sel3DCraft surpasses other T23D systems in supporting creativity for designers.