4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images

• URL: http://arxiv.org/abs/2412.12919v1
• Date: Tue, 17 Dec 2024 13:51:56 GMT
• Title: 4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images
• Authors: Zhentao Liu, Ruyi Zha, Huangxuan Zhao, Hongdong Li, Zhiming Cui,
• Abstract summary: Existing methods often produce suboptimal results or require excessive computation time. We propose 4D radiative Gaussian splatting (4DRGS) to achieve high-quality reconstruction efficiently. 4DRGS achieves impressive results in 5 minutes training, which is 32x faster than the state-of-the-art method.
• Score: 49.170407434313475
• License:
• Abstract: Reconstructing 3D vessel structures from sparse-view dynamic digital subtraction angiography (DSA) images enables accurate medical assessment while reducing radiation exposure. Existing methods often produce suboptimal results or require excessive computation time. In this work, we propose 4D radiative Gaussian splatting (4DRGS) to achieve high-quality reconstruction efficiently. In detail, we represent the vessels with 4D radiative Gaussian kernels. Each kernel has time-invariant geometry parameters, including position, rotation, and scale, to model static vessel structures. The time-dependent central attenuation of each kernel is predicted from a compact neural network to capture the temporal varying response of contrast agent flow. We splat these Gaussian kernels to synthesize DSA images via X-ray rasterization and optimize the model with real captured ones. The final 3D vessel volume is voxelized from the well-trained kernels. Moreover, we introduce accumulated attenuation pruning and bounded scaling activation to improve reconstruction quality. Extensive experiments on real-world patient data demonstrate that 4DRGS achieves impressive results in 5 minutes training, which is 32x faster than the state-of-the-art method. This underscores the potential of 4DRGS for real-world clinics.

Related papers

• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets. Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• 4D Scaffold Gaussian Splatting for Memory Efficient Dynamic Scene Reconstruction [27.455934322535853]
  This paper proposes a 4D anchor-based framework that retains visual quality and rendering speed of 4D Gaussians while reducing storage costs. Experimental results demonstrate that our method achieves state-of-the-art visual quality and 97.8% storage reduction over 4DGS.
  arXiv  Detail & Related papers  (2024-11-26T02:22:07Z)
• LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction [33.794584735264884]
  We introduce a Lightweight 4D Gaussian Splatting framework (LGS) for dynamic endoscopic reconstruction. To minimize the redundancy of Gaussian quantities, we propose Deformation-Aware Pruning. We also simplify the representation of textures and lighting in non-crucial areas by pruning the dimensions of Gaussian attributes.
  arXiv  Detail & Related papers  (2024-06-23T10:49:39Z)
• DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering [30.30749508345767]
  Digitally reconstructed radiographs (DRRs) are simulated 2D X-ray images generated from 3D CT volumes. We present a novel approach that marries realistic physics-inspired X-ray simulation with efficient, differentiable DRR generation.
  arXiv  Detail & Related papers  (2024-06-04T17:39:31Z)
• R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
  3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction. This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
  arXiv  Detail & Related papers  (2024-05-31T08:39:02Z)
• 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images via Vessel Probability Guided Attenuation Learning [79.60829508459753]
  Current commercial Digital Subtraction Angiography (DSA) systems typically demand hundreds of scanning views to perform reconstruction. The dynamic blood flow and insufficient input of sparse-view DSA images present significant challenges to the 3D vessel reconstruction task. We propose to use a time-agnostic vessel probability field to solve this problem effectively.
  arXiv  Detail & Related papers  (2024-05-17T11:23:33Z)
• Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis [88.86777314004044]
  We propose a 3D Gaussian splatting-based framework, namely X-Gaussian, for X-ray novel view visualization. Experiments show that our X-Gaussian outperforms state-of-the-art methods by 6.5 dB while enjoying less than 15% training time and over 73x inference speed.
  arXiv  Detail & Related papers  (2024-03-07T00:12:08Z)
• TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction [34.1903749611458]
  We propose a Time-aware Attenuation Voxel (TiAVox) approach for sparse-view 4D DSA reconstruction. TiAVox introduces 4D attenuation voxel grids, which reflect attenuation properties from both spatial and temporal dimensions. We validated the TiAVox approach on both clinical and simulated datasets.
  arXiv  Detail & Related papers  (2023-09-05T15:34:37Z)
• 4D Spatio-Temporal Convolutional Networks for Object Position Estimation in OCT Volumes [69.62333053044712]
  3D convolutional neural networks (CNNs) have shown promising performance for pose estimation of a marker object using single OCT images. We extend 3D CNNs to 4D-temporal CNNs to evaluate the impact of additional temporal information for marker object tracking.
  arXiv  Detail & Related papers  (2020-07-02T12:02:20Z)

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.