发表机构
Institut de Robòtica i Informàtica Industrial, CSIC-UPC（工业机器人与信息学研究所，西班牙国家研究委员会-加泰罗尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对辐射场方法依赖凸边界问题，提出可变形三角形散列，通过控制点和位移实现非凸形状表示，设计光栅化管道可微渲染，经多种场景验证，在视觉质量、通用性和渲染效率上表现出色。
AI 中文摘要
近期的辐射场方法使用二维基元（从高斯圆盘到三角形）来表示场景，这些基元能实现表面对齐和高效光栅化，但都依赖凸边界，处理弯曲和凹形结构需要过多基元。我们引入可变形三角形散列，每条边用K个控制点增强每个三角形，通过单个可学习标量位移参数化，使边界向内或向外移动，在保留定义3D平面的三个基本顶点的同时实现非凸形状表示。为可微渲染这些非凸基元，我们在三角形重心坐标空间设计光栅化管道，确保视图一致渲染。通过缠绕数测试确定像素是否在变形基元内，由锐度和角平滑度两个可学习参数控制的窗口函数以及每个基元的标量不透明度，产生从内部到边界的平滑不透明度过渡。在各种真实场景中进行验证，在视觉质量和通用性方面优于基于非体积基元的近期工作，同时仍实现有竞争力的渲染效率。
英文摘要
Recent radiance field methods represent scenes with 2D primitives that offer surface alignment and efficient rasterization, from Gaussian disks to triangles, yet all rely on convex boundaries: curved and concave structures demand excessive primitives. We introduce Deformable Triangle Splatting, which augments each triangle with $K$ control points per edge, each parameterized by a single learnable scalar displacement that shifts the boundary inward or outward, enabling non-convex shape representation while preserving the three base vertices that define the 3D plane. To render these non-convex primitives differentiably, we design a rasterization pipeline in the triangle's barycentric coordinate space, ensuring view-consistent rendering. A winding number test determines whether each pixel lies inside the deformed primitive, and a window function controlled by two learnable parameters, sharpness and corner smoothness, together with a per-primitive scalar opacity, produces the smooth opacity transition from interior to boundary. Validation is done in a variety of real-world scenes, outperforming recent works based on non-volumetric primitives in terms of visual quality and versatility while still achieving competitive rendering efficiency.
CommentsAccepted at ECCV 2026. Project page: https://orioljim1.github.io/detris
