DreamPrinting: Volumetric Printing Primitives for High-Fidelity 3D Printing

TL;DR

DreamPrinting bridges radiance-based volumetric rendering and physical 3D printing by introducing Volumetric Printing Primitives (VPPs). It uses the Kubelka–Munk model to map per-voxel pigment concentrations to color and density, calibrates pigments spectrophotometrically, and applies a 3D stochastic halftoning to produce print-ready labels. The method solves a continuous relaxation of discrete pigment labeling and enforces density alignment to reproduce translucency accurately, outperforming surface-based methods on semi-transparent structures. By combining LUT-based pigment mapping with 3D halftoning and integrating with modern 3D generation techniques, DreamPrinting offers a robust framework for high-fidelity, volumetric color prints that reflect their digital radiance origins.

Abstract

Translating the rich visual fidelity of volumetric rendering techniques into physically realizable 3D prints remains an open challenge. We introduce DreamPrinting, a novel pipeline that transforms radiance-based volumetric representations into explicit, material-centric Volumetric Printing Primitives (VPPs). While volumetric rendering primitives (e.g., NeRF) excel at capturing intricate geometry and appearance, they lack the physical constraints necessary for real-world fabrication, such as pigment compatibility and material density. DreamPrinting addresses these challenges by integrating the Kubelka-Munk model with a spectrophotometric calibration process to characterize and mix pigments for accurate reproduction of color and translucency. The result is a continuous-to-discrete mapping that determines optimal pigment concentrations for each voxel, ensuring fidelity to both geometry and optical properties. A 3D stochastic halftoning procedure then converts these concentrations into printable labels, enabling fine-grained control over opacity, texture, and color gradients. Our evaluations show that DreamPrinting achieves exceptional detail in reproducing semi-transparent structures-such as fur, leaves, and clouds-while outperforming traditional surface-based methods in managing translucency and internal consistency. Furthermore, by seamlessly integrating VPPs with cutting-edge 3D generation techniques, DreamPrinting expands the potential for complex, high-quality volumetric prints, providing a robust framework for printing objects that closely mirror their digital origins.

Figures (8)

• Figure 1: Overview of our pipeline for transforming radiance representation into material-centric representation using Volumetric Printing Primitives (VPPs). VPPs are positioned on a uniform grid, storing RGB color and density values to form the pre-print Volume. Color Mapping converts RGB to pigment (C, M, Y, K, W) concentrations, while Density Alignment modifies Cl or K/W concentrations to match target densities. A Stochastic Halftoning Module then assigns discrete pigment labels for direct 3D printing.
• Figure 2: We employ the Volumetric Printing Primitive to bridge the gap between radiance representation and material-centric representation. Using the Kubelka-Munk model, we simulate the pigment mixing process, which serves as the foundation for color calibration and the construction of a printing color gamut with efficient lookup capabilities. This enables the rapid conversion from RGB and density values to pigment concentrations. Finally, we adopt halftoning to generate a print-ready pigment selection.
• Figure 3: Leveraging the properties of VPPs, all operations can be executed in parallel. For each voxel in the radiance representation, expressed in terms of RGB and density, pigment concentrations of C, M, Y, K, and W are determined using a pre-computed color lookup table. Subsequently, a density alignment strategy is applied to adjust the printing density, ensuring alignment with the radiance representation. Finally, stochastic halftoning is employed to generate the print-ready pigment distribution.
• Figure 4: Our results gallery of 3D printing objects from InstantNGPmueller2022instant radiance reconstructions. From left to right: the original images, the 2D images rendering from the radiance reconstruction, and the corresponding 3D printing results.
• Figure 5: Ablation study. "Brute-force" and "w/o Density Alignment" suffer from incomplete opacity. Our method produces accurate opacity, which demonstrates the effectiveness of our density alignment strategy.