Adaptive Multi-resolution Hash-Encoding Framework for INR-based Dental CBCT Reconstruction with Truncated FOV

Hyoung Suk Park; Kiwan Jeon

Home/Archive/arXiv

arXiv · 2506.12471

Adaptive Multi-resolution Hash-Encoding Framework for INR-based Dental CBCT Reconstruction with Truncated FOV

Hyoung Suk Park·Kiwan Jeon

View original source ↗Read source document ↗Export metadata ↓

Abstract

Implicit neural representation (INR), particularly in combination with hash encoding, has recently emerged as a promising approach for computed tomography (CT) image reconstruction. However, directly applying INR techniques to 3D dental cone-beam CT (CBCT) with a truncated field of view (FOV) is challenging. During the training process, if the FOV does not fully encompass the patient's head, a discrepancy arises between the measured projections and the forward projections computed within the truncated domain. This mismatch leads the network to estimate attenuation values inaccurately, producing severe artifacts in the reconstructed images. In this study, we propose a computationally efficient INR-based reconstruction framework that leverages multi-resolution hash encoding for 3D dental CBCT with a truncated FOV. To mitigate truncation artifacts, we train the network over an expanded reconstruction domain that fully encompasses the patient's head. For computational efficiency, we adopt an adaptive training strategy that uses a multi-resolution grid: finer resolution levels and denser sampling inside the truncated FOV, and coarser resolution levels with sparser sampling outside. To maintain consistent input dimensionality of the network across spatially varying resolutions, we introduce an adaptive hash encoder that selectively activates the lower-level features of the hash hierarchy for points outside the truncated FOV. The proposed method with an extended FOV effectively mitigates truncation artifacts. Compared with a naive domain extension using fixed resolution levels and a fixed sampling rate, the adaptive strategy reduces computational time by over 60% for an image volume of 800x800x600, while preserving the PSNR within the truncated FOV.

Explore related subjects

eess.IV cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Hyoung Suk Park, Kiwan Jeon. 2025-06-14. Adaptive Multi-resolution Hash-Encoding Framework for INR-based Dental CBCT Reconstruction with Truncated FOV. https://arxiv.org/abs/2506.12471

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation

This paper addresses cross-modal medical image segmentation, focusing on MRI-CT transfer in a source-only domain generalization setting. During training, only source-modality samples are available, while unlabeled target-modality images are used for testing. We propose LowBridge, which builds on the observation that cross-modal images share similar low-level features (e.g. edges) as they depict the same types of anatomical structures. Specifically, we first train a generative model to recover the source images from their edge features, followed by training a segmentation model on the generated source images, separately. At test time, edge features from the target images are input to the pretrained generative model to generate source-style target domain images, which are then segmented using the pretrained segmentation network. Experiments on various public datasets demonstrate that LowBridge achieves state-of-the-art performance, outperforming ten existing approaches. Ablation studies further show that LowBridge is compatible with different types of generative and segmentation models, suggesting its generalizability and potential to benefit from future advances in these models. The code will be available at https://github.com/JoshuaLPF/LowBridge.

eess.IV↗

arXiv2026

Revolutionizing Diffusion MRI Microstructure Mapping via Global Inversion

Diffusion MRI microstructure mapping (MM) is conventionally solved voxel by voxel, ignoring the fact that tissue microstructure forms a spatially organized field. This isolation leaves each estimation problem ill-posed and nonconvex. We instead cast MM as a single global inverse problem, reconstructing the entire parameter field jointly from all measurements of a subject. An untrained neural representation supplies implicit spatial priors and eases the nonconvex optimization, requiring no training data, while coregistered T1-weighted anatomy contributes structural guidance that is freely available in standard protocols. On both synthetic and in-vivo data, our method compares favorably with established voxel-wise and learning-based baselines, suggesting global inversion is a promising alternative.

eess.IV↗

arXiv2026

LC3EM: Long-Range Context Extrapolation Enhanced Entropy Model for Coordinate-based Overfitting Image Codecs

Coordinate-based overfitting image codecs have attracted increasing attention for their low decoding complexity and independence from cross-image generalization. However, representative approaches such as COOL-CHIC face an inherent entropy-modeling trade-off: lightweight models have limited capacity, while more expressive ones incur additional bitrate overhead from transmitting image-specific parameters. Inspired by the prediction mechanism in traditional codecs, we propose a new entropy-modeling strategy that introduces complementary prediction modes with region-adaptive soft mode selection, rather than relying on a single learned predictor to model diverse types of redundancy. Based on this concept, we develop a Long-Range Context Extrapolation Enhanced Entropy Model (LC3EM), which can be integrated into coordinate-based overfitting codecs. Specifically, a parameter-free Neighborhood-based Linear Extrapolation Mode (NLEM) complements the tiny MLP-based local predictor to exploit long-range contextual redundancy and strongly directional structures. A Minimum-Entropy-Inspired Continuous Mode Selection strategy is designed to adaptively fuse these two complementary modes, while requiring the transmission of only the parameters of a single additional linear layer. Moreover, to alleviate the mismatch between training-time relaxed and actual discrete quantization, we introduce a lightweight iterative latent rounding refinement stage to improve compression performance. Experiments demonstrate consistent improvements across diverse benchmarks, particularly on highly regular computer-generated images. When integrated with COOL-CHIC 4.0, the proposed method achieves BD-rate gains of -3.43\% and -7.69\% on the SIQAD and API datasets, respectively. With COOL-CHIC 5.0 as the backbone, the corresponding gains are -2.88\% and -3.15\%, respectively. The code will be made publicly available soon.

eess.IV↗