Search papers, labs, and topics across Lattice.
This paper introduces $K$-NeAS, a scalable architecture for multi-material CT reconstruction that automates the process of surface reconstruction from sparse projections using a shared latent backbone and a differentiable sequential soft selector. By eliminating the need for manual attenuation tuning through a Gaussian Mixture Model and addressing geometric hallucinations with a scheduled auxiliary floater loss, $K$-NeAS significantly enhances volumetric fidelity and robustness in complex multi-tissue regions. Evaluations on clinical Cone-Beam CT datasets demonstrate that $K$-NeAS achieves a 3D PSNR improvement of $+1.88\text{ dB}$ over single-material baselines while maintaining superior performance under sparse sampling conditions.
Achieving a $+1.88\text{ dB}$ improvement in volumetric fidelity, $K$-NeAS revolutionizes multi-material CT reconstruction by automating attenuation tuning and enhancing robustness against sparse sampling.
Computed Tomography (CT) carries significant ionizing radiation risks, driving the need for sparse-view reconstruction. Implicit scene representations (ISRs) address this by recovering continuous volumetric attenuation fields directly from sparse projections, and recent geometry-aware extensions jointly model surface geometry alongside attenuation to improve fidelity and enable clean tissue segmentation without manual thresholding. However, these methods remain limited by manually tuned attenuation bounds and rigid two-material constraints. This paper proposes $K$-NeAS, a unified and scalable architecture for automated, multi-material surface reconstruction. We replace independent material networks with a shared latent backbone and introduce a fully differentiable $K$-material sequential soft selector to model an arbitrary number of overlapping tissues. To eliminate manual tuning, we automate attenuation bounding using a Gaussian Mixture Model (GMM) and implement a scheduled auxiliary floater loss to mitigate geometric hallucinations common under extreme sparsity. Evaluated across four clinical Cone-Beam CT (CBCT) datasets, $K$-NeAS successfully scales to arbitrary material counts, achieving superior 3D volumetric fidelity at $K=3$ materials on complex multi-tissue regions such as the Abdomen ($33.28\text{ dB}$ 3D PSNR vs. $31.40\text{ dB}$ single-material NeAS baseline, a $+1.88\text{ dB}$ improvement). Furthermore, our model exhibits enhanced robustness under sparse-sampling conditions, outperforming baseline 3D PSNR by up to $1.17\text{ dB}$ under 5- and 10-view constraints.
