# Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstruction

arXiv: https://arxiv.org/abs/2604.27552 · HTML: https://mlsanity.com/paper/2604.27552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Prior](https://mlsanity.com/paper/2001.03799/) (2020)
- [DuDoNet: Dual Domain Network for CT Metal Artifact Reduction](https://mlsanity.com/paper/1907.00273/) (2019)
- [R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction](https://mlsanity.com/paper/2405.20693/) (2024)
- [Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis](https://mlsanity.com/paper/2403.04116/) (2024)
- [Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction](https://mlsanity.com/paper/1803.00694/) (2018)
- [Momentum-Net: Fast and convergent iterative neural network for inverse problems](https://mlsanity.com/paper/1907.11818/) (2019)
- [Generative Modeling in Sinogram Domain for Sparse-view CT Reconstruction](https://mlsanity.com/paper/2211.13926/) (2022)
- [3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation](https://mlsanity.com/paper/2312.15676/) (2023)
- [Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2308.15942/) (2023)

## Abstract (arXiv)

While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view conditions, leading to over-smoothing and a loss of high-frequency anatomical details. Since wavelet transforms provide rich high-frequency information and have been widely utilized to enhance sparse reconstruction, this work integrates wavelet multi-resolution analysis with 3DGS. To circumvent the mathematical mismatch between the strict non-negativity of physical X-ray attenuation and the bipolar nature of high-frequency wavelet coefficients, we propose Residual Gaussian Splatting (RGS). Methodologically, we introduce a spectrally-decoupled Gaussian representation that stratifies the volumetric field into a geometric base component and a residual detail component. This decomposition systematically transforms explicit high-frequency fitting into a physically consistent, implicit residual compensation task. Furthermore, we devise a spectral-spatial collaborative optimization strategy to coordinate the interplay between geometric anchoring and texture refinement, effectively preventing spectral crosstalk. Extensive experiments on clinical datasets demonstrate that RGS enables the reconstructed images to capture highly refined geometric textures. It successfully resolves the trade-off between artifact suppression and detail preservation, yielding superior visual fidelity in complex trabecular and vascular structures compared to existing neural rendering baselines.