arXiv cs.AI· Zihan Deng, Zhenzhen Gong, Yujie Liu, Jiaxin Gong, Dingkun Liu, Kexian Xie, Yixing Huang, Peng Jin, Tianye Niu, Zhisheng Wang, Fenglin Liu, Hongming Shan, Lequan Yu·· 14 小时前AI 评分32
SparseTokenGS：基于可复用 Token 池的高斯稀疏视角 CBCT 重建
SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool
AI 导读
SparseTokenGS 通过可复用 Token 池解决前馈高斯方法在坐标解码时无法调用全扫描信息的问题，Anchor Token Fusion 与 Point-Token Attention 分别在锚点和查询坐标处查询该共享池，单次前向即可完成重建，无需逐扫描优化或投影域损失。
正文 · 原文
Authors:Zihan Deng, Zhenzhen Gong, Yujie Liu, Jiaxin Gong, Dingkun Liu, Kexian Xie, Yixing Huang, Peng Jin, Tianye Niu, Zhisheng Wang, Fenglin Liu, Hongming Shan, Lequan Yu
Abstract:Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts. Feed-forward Gaussian methods transfer the reconstruction cost to training and decode each coordinate from projection-aligned features and neighboring anchors. However, information from the whole scan is written only when the field is constructed and cannot be retrieved during coordinate decoding, leaving the volume inconsistent within the scan. This is a common limitation of such methods: once the field is fixed, decoding uses only local features and reconstruction quality drops substantially. We propose SparseTokenGS, a Gaussian-based method for sparse-view cone-beam computed tomography reconstruction via a reusable token pool. Anchor Token Fusion and Point-Token Attention query this shared pool at the anchors and at the query coordinates, respectively. The local Gaussian prior is retained, and the volume is reconstructed in one forward pass, without per-scan optimization or a projection-domain loss. On three public chest and dental datasets, SparseTokenGS achieves the highest reconstruction performance among the compared methods. On clinical dental scans, reconstruction from only six projections reaches 29.51 decibels in peak signal-to-noise ratio and a structural similarity of 0.842 against the full-view reference, and off-the-shelf tooth-and-pulp segmentation keeps these structures separable for root-canal localization. Experiments on volcanic rock and chicken show performance after same-object adaptation. A reusable token pool gives feed-forward reconstruction a mechanism that keeps scan-wide context available through decoding and can benefit future rapid clinical lesion localization and analysis. The code is available at: this https URL.
| Comments: | 10 pages, 12 figures. Submitted to IEEE Transactions on Medical Imaging |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| MSC classes: | 68U10, 92C55, 65R32 |
| ACM classes: | I.4.5; I.2.10; J.3 |
| Cite as: | arXiv:2610.38360 [cs.CV] |
| (or arXiv:2610.38360v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38360 arXiv-issued DOI via DataCite |
Submission history
From: Zihan Deng [view email]
[v1]
Wed, 28 Oct 2026 06:57:38 UTC (3,769 KB)
来源：arXiv cs.AI · arxiv.org