DReSG：用于风格化高斯溅射的扩散残差
DReSG: Diffusion Residuals for Stylized Gaussian Splatting
浏览论文内容
中文总结 AI 辅助
针对现有3D风格化方法的缺陷，提出DReSG框架，将扩散提议作为残差目标并通过多视图高斯反馈优化，实现稳定可控的参考引导风格化，更好保留场景结构与跨视图稳定性。
中文摘要 AI 辅助
以3D高斯溅射（3DGS）表示的场景的参考引导风格化，对于高效且可控的3D内容创建十分重要。现有基于VGG特征的3D风格化方法能提供稳定的渲染视图优化，但往往未能充分表达富有表现力的参考风格线索；扩散模型具备更强的图像先验，然而直接的逐视图或基于分数的扩散引导会导致视图漂移、局部伪影以及难以控制的外观更新。我们提出DReSG，这是一种用于风格化高斯溅射的3D基残差反馈框架。DReSG将注意力引导的扩散提议表示为相对于当前渲染结果的残差目标，并通过多视图高斯反馈逐步将这些残差吸收到共享高斯场景中。为使该反馈稳定且可控，DReSG在目标构建期间调节残差强度，并在多视图拟合期间结合感知覆盖的视图选择与经冲突过滤的颜色更新。大量实验表明，DReSG在实现具有竞争力的参考引导风格化的同时，能更好地保留场景结构与跨视图稳定性。我们的项目页面可在该https链接获取。
英文摘要
Reference-guided stylization of scenes represented by 3D Gaussian Splatting (3DGS) is important for efficient and controllable 3D content creation. Existing VGG-feature-based 3D stylization methods provide stable rendered-view optimization, but often under-represent expressive reference style cues; diffusion models offer stronger image priors, yet direct per-view or score-based diffusion guidance can lead to view drift, local artifacts, and hard-to-control appearance updates. We present DReSG, a 3D-grounded residual-feedback framework for stylized Gaussian splatting. DReSG represents attention-guided diffusion proposals as residual targets relative to the current render, and progressively absorbs these residuals into a shared Gaussian scene through multi-view Gaussian feedback. To make this feedback stable and controllable, DReSG modulates residual strength during target construction and combines coverage-aware view selection with conflict-filtered color updates during multi-view fitting. Extensive experiments demonstrate that DReSG achieves competitive reference-guided stylization while better preserving scene structure and cross-view stability. Our project page is available at https://vpx-ecnu.github.io/DReSG-website/.
发表机构
- School of Software Engineering, East China Normal University（华东师范大学软件工程学院）
- School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
