Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching
By: Weimin Bai , Yubo Li , Wenzheng Chen and more
Potential Business Impact:
Creates more varied and realistic 3D objects from text.
Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a formulation that inherently favors mode-seeking behavior and limits generation diversity. In this paper, we introduce Dive3D, a novel text-to-3D generation framework that replaces KL-based objectives with Score Implicit Matching (SIM) loss, a score-based objective that effectively mitigates mode collapse. Furthermore, Dive3D integrates both diffusion distillation and reward-guided optimization under a unified divergence perspective. Such reformulation, together with SIM loss, yields significantly more diverse 3D outputs while improving text alignment, human preference, and overall visual fidelity. We validate Dive3D across various 2D-to-3D prompts and find that it consistently outperforms prior methods in qualitative assessments, including diversity, photorealism, and aesthetic appeal. We further evaluate its performance on the GPTEval3D benchmark, comparing against nine state-of-the-art baselines. Dive3D also achieves strong results on quantitative metrics, including text-asset alignment, 3D plausibility, text-geometry consistency, texture quality, and geometric detail.
Similar Papers
Text-to-3D Generation using Jensen-Shannon Score Distillation
CV and Pattern Recognition
Creates better 3D pictures from words.
Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation
CV and Pattern Recognition
Creates realistic 3D objects from text descriptions.
CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback
CV and Pattern Recognition
Makes 3D pictures match words better.