跳到正文
返回论文列表
cs.GR提交于 已译

TetraCoder:面向神经场的自适应四面体编码

TetraCoder: Adaptive Tetrahedral Encoding for Neural Fields

Daniele Della Pietra · Antonella Rech · Nicola Conci · Nicola Garau

中文摘要

几何的隐式与显式表示在计算机图形学应用中各有优劣:显式表示上的表面采样更快,隐式表示上的空间查询更快,因此高效的相互转换极具价值。TetraCoder 是一种单分辨率、无哈希的自适应四面体编码,将显式四面体空间编码器与底层隐式符号距离场(SDF)相连接。由此得到的隐式-显式混合空间在设计上是连续分段仿射(CPWA)的,使隐式 SDF 与显式解析网格之间能够精确对应。该设计还带来额外优势:(a) 由于采用单分辨率可优化网格,其扩展性优于多分辨率编码方法;(b) 与基于哈希的方法不同,它不受碰撞影响;(c) 可直接通过其自适应四面体骨架实现快速四面体光线追踪以及几何与外观编辑。在图像与点云的 2D/3D 拟合、3D 新视角合成、3D 重建以及几何/外观编辑等多项任务上,TetraCoder 相比当前最优方法均有提升,展示了其通用性。

关键要点

  1. 01隐式与显式几何表示各有优劣,高效转换是图形学中的关键需求
  2. 02用单分辨率无哈希自适应四面体编码连接显式编码器与隐式 SDF
  3. 03混合空间为连续分段仿射,实现 SDF 与解析网格的精确对应
  4. 04单分辨率网格扩展性更好,且无哈希碰撞问题
  5. 05支持快速四面体光线追踪与几何/外观编辑,多项任务优于当前最优

解读

尚无解读。

原始英文摘要

arXiv:2611.18267v1 Announce Type: cross Abstract: Implicit and explicit representations of geometry are central in computer graphics applications and come with their pros and cons. With surface sampling being faster on explicit representations and spatial queries being faster on implicit representations, finding efficient conversions between them is a highly desirable property. We present TetraCoder, a single resolution hash-free adaptive tetrahedral encoding that links an explicit tetrahedral spatial encoder with an underlying implicit signed distance field (SDF). The resulting hybrid implicit-explicit space is continuous piecewise affine (CPWA) by design, allowing to obtain an exact correspondence between the implicit SDF and the explicit analytic mesh. TetraCoder's design comes with additional perks, in particular: (a) it scales better than multi-resolution encoding methods due to its single resolution optimizable grid, (b) unlike hash-based methods, it is not affected by collisions, (c) it enables fast tetrahedral ray-tracing, geometry and appearance editing, directly through its adaptive tetrahedral scaffold. We demonstrate the versatility of TetraCoder by showing an improvement over state-of-the-art methods on multiple tasks: 2D/3D fitting from images and point clouds, 3D novel view synthesis, 3D reconstruction, and geometry/appearance editing.

同方向论文 · cs.GR

查看全部 →