In this work we present a novel multi-view photometric stereo (PS) method.
Like many works in 3D reconstruction we are leveraging neural shape
representations and learnt renderers. However, our work differs from the
state-of-the-art multi-view PS methods such as PS-NeRF or SuperNormal we
explicity leverage per-pixel intensity renderings rather than relying mainly on
estimated normals.
We model point light attenuation and explicitly raytrace cast shadows in
order to best approximate each points incoming radiance. This is used as input
to a fully neural material renderer that uses minimal prior assumptions and it
is jointly optimised with the surface. Finally, estimated normal and
segmentation maps can also incorporated in order to maximise the surface
accuracy.
Our method is among the first to outperform the classical approach of
DiLiGenT-MV and achieves average 0.2mm Chamfer distance for objects imaged at
approx 1.5m distance away with approximate 400x400 resolution. Moreover, we
show robustness to poor normals in low light count scenario, achieving 0.27mm
Chamfer distance when pixel rendering is used instead of estimated normals.

我们提出了一种新颖的多视图光度立体（PS）方法，利用神经形状表示和学习渲染器，显式利用像素强度渲染，模拟每个点的入射辐照度并使用全神经材质渲染器进行优化，同时通过估计法线和分割图最大化表面精度，达到在距离为 1.5m、分辨率 400x400 的情况下，超过经典方法 DiLiGenT-MV 的平均 0.2mm 的沙耶缝距离，对低光计数场景的异常法线具有鲁棒性，使用像素渲染距离仅为 0.27mm。