Poxel: Voxel Reconstruction for 3D Printing
Ruixiang Cao, Satoshi Yagi, Satoshi Yamamori, Jun Morimoto
TL;DR
The paper addresses the mismatch between digitally optimized, view-dependent 3D reconstructions (e.g., NeRF, Plenoxel, 3D Gaussian Splatting) and the needs of physical 3D printing. It introduces Poxel, a printable-voxel framework that outputs CMYKWCl-encoded voxels, eliminates view-dependency, and uses anisotropic voxels with region-based color averaging to enable high-fidelity, full-color prints on multi-material photopolymer jetting systems. A loss-driven optimization aligns discrete CMYKWCl colors with voxel neighborhoods, including a region color-averaging mechanism $\bar{C} = \frac{1}{N} \sum_{i=1}^{N} C_i$ with $N = 12$, to ensure smooth color transitions. Experimental results on a Stratasys J850 show that Poxel achieves superior print fidelity and color accuracy compared with a 3D Gaussian Splatting baseline, demonstrating a practical pathway from digital reconstructions to accurate physical objects.
Abstract
Recent advancements in 3D reconstruction, especially through neural rendering approaches like Neural Radiance Fields (NeRF) and Plenoxel, have led to high-quality 3D visualizations. However, these methods are optimized for digital environments and employ view-dependent color models (RGB) and 2D splatting techniques, which do not translate well to physical 3D printing. This paper introduces "Poxel", which stands for Printable-Voxel, a voxel-based 3D reconstruction framework optimized for photopolymer jetting 3D printing, which allows for high-resolution, full-color 3D models using a CMYKWCl color model. Our framework directly outputs printable voxel grids by removing view-dependency and converting the digital RGB color space to a physical CMYKWCl color space suitable for multi-material jetting. The proposed system achieves better fidelity and quality in printed models, aligning with the requirements of physical 3D objects.