$K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs

• URL: http://arxiv.org/abs/2607.14415v1
• Date: Wed, 15 Jul 2026 23:08:45 GMT
• Title: $K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs
• Abstract summary: Implicit scene representations (ISRs) address this by recovering continuous volumetric attenuation fields directly from sparse projections.<n>This paper proposes $K$-NeAS, a unified and scalable architecture for automated, multi-material surface reconstruction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing [0.5626158829476339]
  Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue.<n>On the BraTS local-synthesis benchmark, which ranks submissions on the structural similarity index (SSIM), the peak signal-to-noise ratio, and the mean squared error (MSE) jointly, the strongest recent models are accurate.<n>We address this in post-processing, forming a deep ensemble of the two co-first-place 2025 models and training a lightweight residual refiner on the ensemble's own outputs.
  arXiv  Detail & Related papers  (2026-09-03T15:13:59Z)
• WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment [50.39311913179626]
  We present WearWow, an end-to-end, mask-free generative framework that pioneers ultra-high-resolution multi-garment synthesis.<n>To mitigate the memory explosion, we propose Adaptive 2D Token Packing (ATP)<n>To rectify texture degradation, we introduce the Multi-dimensional Try-on Reward (MTR)
  arXiv  Detail & Related papers  (2026-07-22T08:55:52Z)
• PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation [105.86385617182879]
  State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions.<n>We show that such architectural overhead and intricate loss formulations are unnecessary.<n>We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches.
  arXiv  Detail & Related papers  (2026-07-02T17:59:56Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction [4.107377779783183]
  We propose Conditional Posterior Alignment (CDPA) to enable scalable 3D sparse-view CT reconstruction.<n>A 2D U-Net diffusion model is conditioned on an initial 3D reconstruction to improve inter-slice consistency.<n> Experiments on synthetic and real Cone Beam CT (CBCT) data show state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-23T14:09:13Z)
• SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization [3.5109108807229403]
  We propose SA-CycleGAN-2.5D, a domain adaptation framework motivated by the $HH$-divergence bound of Ben-David et al.<n>By bridging 2D efficiency and 3D consistency, our framework yields voxel-level harmonized images that preserve tumor pathophysiology.
  arXiv  Detail & Related papers  (2026-03-17T23:49:46Z)
• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting [63.138778159026934]
  We propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO.<n> ERGO dynamically estimates the view-specific excess risk and adaptively adjust loss weights during optimization.<n>Experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T20:44:43Z)
• GANeXt: A Fully ConvNeXt-Enhanced Generative Adversarial Network for MRI- and CBCT-to-CT Synthesis [4.966806084618106]
  We propose GANeXt, a 3D patch-based, fully ConvNeXt-powered generative adversarial network for unified CT synthesis.<n>Specifically, GANeXt employs an efficient U-shaped generator constructed from stacked 3D ConvNeXt blocks with compact kernels.<n>To improve synthesis quality, we incorporate a combination of loss functions, including mean absolute error (MAE), perceptual loss, segmentation-based masked MAE, and adversarial loss.
  arXiv  Detail & Related papers  (2025-12-22T12:32:16Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling [79.56581753856452]
  SparseFlex is a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $10243$ directly from rendering losses.<n>By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.
  arXiv  Detail & Related papers  (2025-03-27T17:46:42Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications.<n>Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas.<n>We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis [55.561961365113554]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS)<n>In this paper, we introduce Self-Ensembling Gaussian Splatting (SE-GS)<n>We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training.<n> Experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets demonstrate that our approach enhances NVS quality under few-shot training conditions.
  arXiv  Detail & Related papers  (2024-10-31T18:43:48Z)
• Limited Angle Tomography for Transmission X-Ray Microscopy Using Deep Learning [12.991428974915795]
  Deep learning is applied to limited angle reconstruction in X-ray microscopy for the first time. The U-Net, the state-of-the-art neural network in biomedical imaging, is trained from synthetic data. The proposed method remarkably improves the 3-D visualization of the subcellular structures in the chlorella cell.
  arXiv  Detail & Related papers  (2020-01-08T12:11:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.