We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.
Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
#3 best model for 3D Reconstruction on Data3D−R2N2 (using extra training data)
Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object.
We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making use of differentiable point cloud renderer to train with 2D supervision.