Publication
Reconstructing the Surface of Inhomogeneous Transparent Scenes by Scatter Trace Photography
AbstractWe present a new method for reconstructing the exterior surface of a complex transparent scene with inhomogeneous interior (e.g., multiple interfaces, reflective or painted interiors, etc). Our approach involves capturing images of the scene from one or more viewpoints while moving a proximal light source to a 2D or 3D set of positions. This gives a 2D (or 3D) dataset per pixel, called the scatter trace. The key idea of our approach is that even though light transport within a transparent scene’s interior can be exceedingly complex, the scatter trace of each pixel has a highlyconstrained geometry that (1) reveals the contribution of direct surface reflection, and (2) leads to a simple “scatter-trace stereo” algorithm for computing the local geometry of the exterior surface (depth and surface normals). We present 3D reconstruction results for a variety of scenes that exhibit complex light transport phenomena.
Download publicationRelated Resources
See what’s new.
2025
In-Context Imitation Learning via Next-Token PredictionThis robotics approach allows flexible and training-free execution of…
2024
XLB: A Differentiable Massively Parallel Lattice Boltzmann Library in PythonThis research introduces the XLB library, a scalable Python-based…
2016
Automated Extraction of System Structure Knowledge from TextThis paper presents a method to automatically extract structure…
2010
DeskCube: using Physical Zones to Select and Control Combinations of 3D Navigation OperationsWe present the DeskCube, a new passive input device, together with a…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us