Contrastive preference optimization, combining ImageReward and PickScore with static and LLM-generated negative prompts, improves semantic alignment in SDS-based 3D human generation, especially for long prompts.
X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recent advancements in automatic 3D avatar generation guided by text have made significant progress. However, existing methods have limitations such as oversaturation and low-quality output. To address these challenges, we propose X-Oscar, a progressive framework for generating high-quality animatable avatars from text prompts. It follows a sequential Geometry->Texture->Animation paradigm, simplifying optimization through step-by-step generation. To tackle oversaturation, we introduce Adaptive Variational Parameter (AVP), representing avatars as an adaptive distribution during training. Additionally, we present Avatar-aware Score Distillation Sampling (ASDS), a novel technique that incorporates avatar-aware noise into rendered images for improved generation quality during optimization. Extensive evaluations confirm the superiority of X-Oscar over existing text-to-3D and text-to-avatar approaches. Our anonymous project page: https://xmu-xiaoma666.github.io/Projects/X-Oscar/.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Text-driven 3D Human Generation via Contrastive Preference Optimization
Contrastive preference optimization, combining ImageReward and PickScore with static and LLM-generated negative prompts, improves semantic alignment in SDS-based 3D human generation, especially for long prompts.