OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields

TL;DR

OReX is a neural field-based method for reconstructing 3D shapes from planar cross-sections, addressing high-frequency detail challenges with hierarchical sampling and gradient regularization, achieving state-of-the-art results.

Contribution

The paper introduces a novel neural field approach with iterative and hierarchical sampling schemes for improved 3D shape reconstruction from slices alone.

Findings

Robust and accurate reconstruction demonstrated through extensive experiments.

Achieves state-of-the-art results compared to previous methods.

Effective mitigation of high-frequency detail loss and ripple effects.

Abstract

Reconstructing 3D shapes from planar cross-sections is a challenge inspired by downstream applications like medical imaging and geographic informatics. The input is an in/out indicator function fully defined on a sparse collection of planes in space, and the output is an interpolation of the indicator function to the entire volume. Previous works addressing this sparse and ill-posed problem either produce low quality results, or rely on additional priors such as target topology, appearance information, or input normal directions. In this paper, we present OReX, a method for 3D shape reconstruction from slices alone, featuring a Neural Field as the interpolation prior. A modest neural network is trained on the input planes to return an inside/outside estimate for a given 3D coordinate, yielding a powerful prior that induces smoothness and self-similarities. The main challenge for this approach is high-frequency details, as the neural prior is overly smoothing. To alleviate this, we offer an iterative estimation architecture and a hierarchical input sampling scheme that encourage coarse-to-fine training, allowing the training process to focus on high frequencies at later stages. In addition, we identify and analyze a ripple-like effect stemming from the mesh extraction step. We mitigate it by regularizing the spatial gradients of the indicator function around input in/out boundaries during network training, tackling the problem at the root. Through extensive qualitative and quantitative experimentation, we demonstrate our method is robust, accurate, and scales well with the size of the input. We report state-of-the-art results compared to previous approaches and recent potential solutions, and demonstrate the benefit of our individual contributions through analysis and ablation studies.