Edge-preserving Near-light Photometric Stereo with Neural Surfaces
This work addresses edge preservation in photometric stereo for applications requiring detailed 3D shape recovery, representing an incremental improvement over previous methods.
The paper tackles the problem of preserving sharp depth edges in near-light photometric stereo 3D reconstruction by introducing an analytically differentiable neural surface to avoid differentiation errors, resulting in effective detailed shape recovery as demonstrated in experiments on synthetic and real-world scenes.
This paper presents a near-light photometric stereo method that faithfully preserves sharp depth edges in the 3D reconstruction. Unlike previous methods that rely on finite differentiation for approximating depth partial derivatives and surface normals, we introduce an analytically differentiable neural surface in near-light photometric stereo for avoiding differentiation errors at sharp depth edges, where the depth is represented as a neural function of the image coordinates. By further formulating the Lambertian albedo as a dependent variable resulting from the surface normal and depth, our method is insusceptible to inaccurate depth initialization. Experiments on both synthetic and real-world scenes demonstrate the effectiveness of our method for detailed shape recovery with edge preservation.