Dive3D shows that replacing KL divergence with score implicit matching in text-to-3D distillation, together with a reward term, produces more diverse and higher-fidelity 3D assets than SDS and ProlificDreamer baselines.
threestudio: A unified framework for 3d content generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching
Dive3D shows that replacing KL divergence with score implicit matching in text-to-3D distillation, together with a reward term, produces more diverse and higher-fidelity 3D assets than SDS and ProlificDreamer baselines.