3D Splatting gaussiano (3DGS) excels in photorealistic scene reconstruction
but struggles with stylized scenarios (per esempio., cartoni animati, giochi) due to fragmented
textures, disallineamento semantico, and limited adaptability to abstract
aesthetics. Proponiamo StyleMe3D, a holistic framework for 3D GS style transfer
that integrates multi-modal style conditioning, multi-level semantic alignment,
and perceptual quality enhancement. Our key insights include: (1) optimizing
only RGB attributes preserves geometric integrity during stylization; (2)
disentangling low-, medium-, and high-level semantics is critical for coherent
style transfer; (3) scalability across isolated objects and complex scenes is
essential for practical deployment. StyleMe3D introduces four novel components:
Dynamic Style Score Distillation (DSSD), leveraging Stable Diffusion’s latent
space for semantic alignment; Contrastive Style Descriptor (CSD) for localized,
content-aware texture transfer; Simultaneously Optimized Scale (SOS) to
decouple style details and structural coherence; and 3D Gaussian Quality
Assessment (3DG-QA), a differentiable aesthetic prior trained on human-rated
data to suppress artifacts and enhance visual harmony. Evaluated on NeRF
synthetic dataset (objects) and tandt db (scenes) datasets, StyleMe3D
outperforms state-of-the-art methods in preserving geometric details (per esempio.,
carvings on sculptures) and ensuring stylistic consistency across scenes (per esempio.,
coherent lighting in landscapes), while maintaining real-time rendering. Questo
work bridges photorealistic 3D GS and artistic stylization, unlocking
applications in gaming, virtual worlds, and digital art.

Questo articolo esplora i giri e le loro implicazioni.

Scarica PDF: