Full 3D Reconstruction of Transparent Objects
This addresses a significant gap in computer vision for applications like robotics and graphics, though it is incremental as it builds on space carving and optimization techniques.
The paper tackles the problem of 3D reconstruction for transparent objects, which existing methods cannot handle, by developing a fully automatic approach that captures silhouettes and light refraction paths to optimize a model under multiple constraints, successfully recovering complex shapes and reproducing light refraction properties in experiments.
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing complete 3D shapes of transparent objects. Through positioning an object on a turntable, its silhouettes and light refraction paths under different viewing directions are captured. Then, starting from an initial rough model generated from space carving, our algorithm progressively optimizes the model under three constraints: surface and refraction normal consistency, surface projection and silhouette consistency, and surface smoothness. Experimental results on both synthetic and real objects demonstrate that our method can successfully recover the complex shapes of transparent objects and faithfully reproduce their light refraction properties.