CVGRSep 6, 2018

Surface Light Field Fusion

arXiv:1809.02057v114 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of scanning reflective objects for applications in computer vision and graphics, representing an incremental improvement over existing methods.

The paper tackles the problem of interactively scanning highly reflective objects using a commodity RGBD sensor by modeling the surface light field, which encodes scene appearance from all directions. The result is a robust representation that achieves high-quality results by factoring the surface light field into view-independent and wavelength-independent components.

We present an approach for interactively scanning highly reflective objects with a commodity RGBD sensor. In addition to shape, our approach models the surface light field, encoding scene appearance from all directions. By factoring the surface light field into view-independent and wavelength-independent components, we arrive at a representation that can be robustly estimated with IR-equipped commodity depth sensors, and achieves high quality results.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes