M3GStyler: Enhancing consistency across multi-view in multi-modality 3D Gaussian style transfer

Xueqi Qiu, Xingyu Miao, Haoran Duan, Minye Shao, Bing Zhai, Gongjie Zhang, Jingjing Deng, Yang Long · Pattern Recognition · 2026

• Unified text- and image-guided 3D style transfer with consistent views across a scene, while preserving fine details. • Flow-based feature matching aligns text and image cues for faithful style. • Parallel frequency branches balance structure (low frequency) and detail (high frequency). • Cross-dimension and texture losses improve color and texture fidelity.

Read the paper · More papers on PaperTik