10. robust energy minimization for brdf-invariant shape from light fields

Department: Computer Science & Engineering
Research Institute Affiliation: Agile Center for Visual Computing
Faculty Advisor(s): Manmohan Chandraker | Ravi Ramamoorthi

Primary Student
Name: Zhengqin Li
Email: zhl378@ucsd.edu
Phone: 858-822-3319
Grad Year: 2021

Student Collaborators
Zexiang Xu, zex014@eng.ucsd.edu

Highly effective optimization frameworks have been developed for traditional multiview stereo relying on diffuse photoconsistency, however, they do not account for complex material properties. On the other hand, recent works have explored PDE invariants for shape recovery with complex BRDFs, but they have not been incorporated into robust numerical optimization frameworks. We present a variational energy minimization framework for robust recovery of shape in multiview stereo with complex, unknown BRDFs. While our formulation is general, we demonstrate its efficacy on shape recovery using a single light field image, where the microlens array may be considered as a realization of a purely translational multiview stereo setup. Our formulation automatically balances contributions from texture gradients, traditional Lambertian photoconsistency, an appropriate BRDF-invariant PDE and a smoothness prior. Unlike prior works, our energy function inherently handles spatially-varying BRDFs and albedos. It also uniformly handles both wide and narrow baseline configurations, using the former for better triangulation and the latter for better correspondence while imposing BRDF-invariance. Extensive experiments with synthetic and real data show that our optimization framework consistently achieves errors lower than Lambertian baselines and further, is more robust than prior BRDF-invariant reconstruction methods.

Industry Application Area(s)
computer vision

« Back to Posters or Search Results