让3D高分辨率场景实现风格迁移，效果更逼真。
SGSST: Scaling Gaussian Splatting StyleTransfer
- 基于多尺度全局神经统计的优化损失，提升风格迁移效果。
- 可在超高分辨率3D场景上实现稳定风格迁移，支持大尺寸图像。
- 适合需要高质量3D内容生成的研究者与视觉设计师。
将风格迁移应用于完整3D环境是一项挑战性任务，自神经渲染出现以来已取得诸多进展。3D高斯泼溅（3DGS）近期在训练速度和重建质量方面大幅推进了神经渲染的边界。本文提出SGSST：Scaling Gaussian Splatting Style Transfer，一种基于优化的方法，用于对预训练的3DGS场景进行风格迁移。我们引入一种名为SOS（Simultaneously Optimized Scales）的新多尺度损失，该损失基于全局神经统计，使风格迁移可扩展至超高清3D场景。SGSST不仅首次在如此高分辨率下实现3D场景风格迁移，且在定性、定量及感知评估中均表现出更优的视觉质量。
原文摘要 · Abstract (English)
Applying style transfer to a full 3D environment is a challenging task that has seen many developments since the advent of neural rendering. 3D Gaussian splatting (3DGS) has recently pushed further many limits of neural rendering in terms of training speed and reconstruction quality. This work introduces SGSST: Scaling Gaussian Splatting Style Transfer, an optimization-based method to apply style transfer to pretrained 3DGS scenes. We demonstrate that a new multiscale loss based on global neural statistics, that we name SOS for Simultaneously Optimized Scales, enables style transfer to ultra-high resolution 3D scenes. Not only SGSST pioneers 3D scene style transfer at such high image resolutions, it also produces superior visual quality as assessed by thorough qualitative, quantitative and perceptual comparisons.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。