跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20283 · v2

CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images

首次提交 2026-11-16 06:25
版本更新 2026-11-18 07:30
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

We present a method for inferring the interior temperature distribution of a solid object from registered multi-view visible-spectrum and thermal images, even when the thermal views cover only part of its surface. We formulate steady-state heat conduction as a Laplace boundary value problem and solve it with a direct boundary integral equation discretized over a point cloud: a Gaussian reconstruction of the visible-spectrum images supplies the boundary geometry, and the thermal images supply the boundary data. We do not build surface or volume meshes at any stage in our method. Instead, we sample collocation points from rendered depth without the pixels at depth discontinuities, and use a density subtraction that keeps the interior evaluation accurate up to the surface. The whole chain is differentiable, and we use it to recover the pose and depth of heating pipes, insulation defects, and the shape of cracks from thermal images. We validate our method through experiments on boundary value problems with Dirichlet-only and mixed Dirichlet and Robin boundaries, using synthetic and real captured data on scenes with challenging topology. These experiments show that our method matches analytical solutions and has better accuracy than FEM solvers.

作者备注:18 pages; correct an author's name

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

仅对比实际观测的元数据,不代表 PDF 正文或实验变化。版本可能不连续;带删除线为移除,下划线为新增。

作者变化

Liu Zhenyuan,Bharath Seshadri,Bailey Miller,George Kopanas,IonnaisIoannis Gkioulekas,Bernd Bickel

作者备注变化

18 pages; correct an author's name

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 07:30 · 最新观测版本

CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images

We present a method for inferring the interior temperature distribution of a solid object from registered multi-view visible-spectrum and thermal images, even when the thermal views cover only part of its surface. We formulate steady-state heat conduction as a Laplace boundary value problem and solve it with a direct boundary integral equation discretized over a point cloud: a Gaussian reconstruction of the visible-spectrum images supplies the boundary geometry, and the thermal images supply the boundary data. We do not build surface or volume meshes at any stage in our method. Instead, we sample collocation points from rendered depth without the pixels at depth discontinuities, and use a density subtraction that keeps the interior evaluation accurate up to the surface. The whole chain is differentiable, and we use it to recover the pose and depth of heating pipes, insulation defects, and the shape of cracks from thermal images. We validate our method through experiments on boundary value problems with Dirichlet-only and mixed Dirichlet and Robin boundaries, using synthetic and real captured data on scenes with challenging topology. These experiments show that our method matches analytical solutions and has better accuracy than FEM solvers.

查看此版本解读 →查看此版本原文 ↗
v1 · 2026-11-16 06:25

CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images

We present a method for inferring the interior temperature distribution of a solid object from registered multi-view visible-spectrum and thermal images, even when the thermal views cover only part of its surface. We formulate steady-state heat conduction as a Laplace boundary value problem and solve it with a direct boundary integral equation discretized over a point cloud: a Gaussian reconstruction of the visible-spectrum images supplies the boundary geometry, and the thermal images supply the boundary data. We do not build surface or volume meshes at any stage in our method. Instead, we sample collocation points from rendered depth without the pixels at depth discontinuities, and use a density subtraction that keeps the interior evaluation accurate up to the surface. The whole chain is differentiable, and we use it to recover the pose and depth of heating pipes, insulation defects, and the shape of cracks from thermal images. We validate our method through experiments on boundary value problems with Dirichlet-only and mixed Dirichlet and Robin boundaries, using synthetic and real captured data on scenes with challenging topology. These experiments show that our method matches analytical solutions and has better accuracy than FEM solvers.

查看此版本解读 →查看此版本原文 ↗