CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback

Chenhan Jiang; Yihan Zeng; Dit-Yan Yeung

AAAI 2026technical0 citations

CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback

Chenhan Jiang, Yihan Zeng, Dit-Yan Yeung

Abstract

Score Distillation Sampling (SDS) has achieved remarkable success in text-to-3D content generation. However, SDS-based methods struggle to maintain semantic fidelity for user prompts, particularly when involving multiple objects with intricate interactions. While existing approaches often address 3D consistency through multiview diffusion model fine-tuning on 3D datasets, this strategy inadvertently exacerbates text-3D alignment degradation. The limitation stems from SDS

BibTeX

@inproceedings{aaai2026_coherendreamboos,
  title = {CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback},
  author = {Chenhan Jiang and Yihan Zeng and Dit-Yan Yeung},
  booktitle = {AAAI 2026},
  year = {2026}
}