TexGS-VolVis：通过纹理化高斯溅射实现面向体可视化的表现性场景编辑
TexGS-VolVis: Expressive Scene Editing for Volume Visualization via Textured Gaussian Splatting
AI总结：
本文提出TexGS-VolVis框架，通过二维纹理化高斯溅射结合预训练大模型，实现体可视化的任意风格迁移、实时渲染与细粒度可控场景编辑，并在效率、质量和灵活性上优于现有方法。
摘要：
体可视化（VolVis）的进展侧重于从三维体数据中提取洞见，通过生成具有视觉吸引力的渲染结果来揭示复杂的内部结构。现有的体可视化方法探索了非真实感渲染技术，以增强视觉传达的清晰度、表现力和信息量。尽管这些方法有效，但它们通常依赖复杂的预定义规则，并且仅限于迁移单一风格，限制了其灵活性。为克服这些局限，我们主张使用可微分高斯基元并结合预训练大模型来表示体可视化场景，从而实现任意风格迁移和实时渲染。然而，传统的三维高斯基元将几何与外观紧密耦合，导致风格化结果不够理想。为此，我们提出了TexGS-VolVis，一个面向体可视化的纹理化高斯溅射框架。TexGS-VolVis采用二维高斯基元，为每个高斯扩展额外的纹理和着色属性，从而在推理过程中实现更高质量、几何一致的风格化以及增强的光照控制。尽管取得了这些改进，实现灵活且可控的场景编辑仍然具有挑战性。为进一步增强风格化，我们开发了专为TexGS-VolVis定制的图像驱动和文本驱动的非真实感场景编辑，以及二维提升到三维的分割方法，以实现具有细粒度控制的部分编辑。我们在多种体渲染场景中对TexGS-VolVis进行了定性和定量评估，证明其在效率、视觉质量和编辑灵活性方面优于现有方法。
英文摘要：
Advancements in volume visualization (VolVis) focus on extracting insights from 3D volumetric data by generating visually compelling renderings that reveal complex internal structures. Existing VolVis approaches have explored non-photorealistic rendering techniques to enhance the clarity, expressiveness, and informativeness of visual communication. While effective, these methods often rely on complex predefined rules and are limited to transferring a single style, restricting their flexibility. To overcome these limitations, we advocate the representation of VolVis scenes using differentiable Gaussian primitives combined with pretrained large models to enable arbitrary style transfer and real-time rendering. However, conventional 3D Gaussian primitives tightly couple geometry and appearance, leading to suboptimal stylization results. To address this, we introduce TexGS-VolVis, a textured Gaussian splatting framework for VolVis. TexGS-VolVis employs 2D Gaussian primitives, extending each Gaussian with additional texture and shading attributes, resulting in higher-quality, geometry-consistent stylization and enhanced lighting control during inference. Despite these improvements, achieving flexible and controllable scene editing remains challenging. To further enhance stylization, we develop image- and text-driven non-photorealistic scene editing tailored for TexGS-VolVis and 2D-lift-3D segmentation to enable partial editing with fine-grained control. We evaluate TexGS-VolVis both qualitatively and quantitatively across various volume rendering scenes, demonstrating its superiority over existing methods in terms of efficiency, visual quality, and editing flexibility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
