Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation.

Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods.

The ENL metric measures the smoothness in the homogeneous regions.

It consists of reconstructing a 3D tomogram from captured 2D projections of the scanned sample.

To address this issue, we propose a novel rectification technique via refactoring the projection from 3D to 2D Gaussians.