Non-Local Guided Neural Fields for 4D CT Reconstruction

Dynamic CT reconstruction plays a crucial role in both medical and industrial applications. However, existing 4D CT reconstruction methods typically rely on complex regularization techniques or external large-scale training datasets, posing challenges for reconstruction quality and generalization when handling complex object motion and varied imaging modes. Neural Radiance Fields (NeRF) offer a promising approach to dynamic CT reconstruction, but existing NeRF-based methods often assume that the scene is low-rank, limiting their representation capabilities. To address these issues, we propose NG-NeRF. First, we combine 3D and 4D hash grids for scene representation, effectively reducing temporal redundancy in static regions of dynamic scenes while improving the model’s representation capabilities and efficiency. Next, we design a non-local hash attention module to establish non-local dependencies between the features of different hash grids. This guides the model to adaptively select features based on hash table load information, significantly alleviating hash collisions and achieving the decoupling of dynamic and static regions. Besides, we introduce global continuity by employing mask positional encoding, which helps reduce the noise often introduced by grid features. Our experimental results on medical and industrial datasets demonstrate that the proposed method outperforms existing state-of-the-art methods by 5.84 dB and 3.4 dB, respectively, and exhibits excellent generalization ability across different 4D CT scenarios.