DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction
Authors: Shiyu Zhang, Zhicong Wu, Huangxuan Zhao, Zhentao Liu, Lei Chen, Yong Luo, Lefei Zhang, Zhiming Cui, +2 more
Organizations: School of Computer Science, Wuhan University, Wuhan, China · Institute of Artificial Intelligence, Xiamen University, Xiamen, China · School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China · Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advancements in gaussian splatting and dynamic neural representations have enabled robust 3D vessel reconstruction from sparse dynamic inputs. However, these methods are fundamentally constrained by the resolution of input projections, where performing naive upsampling to enhance rendering resolution inevitably results in severe blurring and aliasing artifacts. Such lack of super-resolution capability prevents the reconstructed 4D models from recovering fine-grained vascular details and intricate branching structures, which restricts their application in precision diagnosis and treatment. To solve this problem, this paper proposes DSA-SRGS, the first super-resolution gaussian splatting framework for dynamic sparse-view DSA reconstruction. Specifically, we introduce a Multi-Fidelity Texture Learning Module that integrates high-quality priors from a fine-tuned DSA-specific super-resolution model, into the 4D reconstruction optimization. To mitigate potential hallucination artifacts from pseudo-labels, this module employs a Confidence-Aware Strategy to adaptively weight supervision signals between the original low-resolution projections and the generated high-resolution pseudo-labels. Furthermore, we develop Radiative Sub-Pixel Densification, an adaptive strategy that leverages gradient accumulation from high-resolution sub-pixel sampling to refine the 4D radiative gaussian kernels. Extensive experiments on two clinical DSA datasets demonstrate that DSA-SRGS significantly outperforms state-of-the-art methods in both quantitative metrics and qualitative visual fidelity.
Figures & tables
Figure 1: Overview of traditional post-upsampling paradigm vs. our DSA-SRGS.
Figure 2: Architecture of the proposed DSA-SRGS.
View
Method
DSA-28
DSA-15
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
30
R 2 -Gaussian
28.163
0.7895
28.499
0.7871
TOGS
33.338
0.8362
33.273
0.8349
4DRGS
33.819
0.8541
33.687
0.8433
Ours
34.323
0.8563
34.198
0.8543
40
R 2 -Gaussian
28.394
0.7947
28.716
0.7934
Table 1: Comparison with other reconstruction methods. Bold indicates the best results. Underline indicates the second-best result.
Figure 3: Qualitative comparison of different models..
Components
DSA-28
DSA-15
Baseline
SR
BS
PL
MF
C
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
✓
33.163
0.8405
33.819
0.8541
✓
✓
✓
33.243
0.8417
34.030
0.8543
✓
✓
✓
33.533
0.8312
34.144
0.8214
✓
✓
✓
✓
33.572
0.8493
34.223
0.8537
✓
✓
✓
✓
33.673
0.8504
34.287
0.8544
Table 2: Ablation Study of Core Components for DSA-SRGS. SR: SR Rendering, BS: Blurry Supervision, PL: Pseudo-label, MF: Multi-fidelity Learning, C: Confidence.
SR Model
DSA-28
DSA-15
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
SwinIR [ 15 ]
33.547
0.8479
34.190
0.8536
Real-ESRGAN [ 27 ]
32.988
0.8430
33.601
0.8468
EDT [ 14 ]
33.536
0.8475
34.176
0.8526
HAT [ 3 ]
33.526
0.8485
34.164
0.8532
Mambair [ 9 ]
33.621
0.8499
34.253
0.8554
Table 3: Quantitative comparison of super-resolution models.
Digital Subtraction Angiography (DSA) is one of the gold standards for vascular disease diagnosis. With the help of a contrast agent, time-resolved 2D DSA images deliver comprehensive blood flow information and can be utilized to reconstruct 3D vessel structures for medical assessment. Current commercial DSA systems typically require hundreds of scanning views to perform reconstruction, resulting in substantial radiation exposure. In this study, we propose a neural rendering-based optimization framework tailored for high-quality sparse-view DSA reconstruction to reduce radiation dosage. Our approach, termed vessel probability guided attenuation learning, represents DSA imaging as a complementary weighted combination of static and dynamic attenuation fields, with the weights derived from the time-independent vessel probability field. Functioning as a foreground mask, vessel probability provides proper gradients for both static and dynamic fields adaptive to different scene types. This mechanism enables self-supervised decomposition between static backgrounds and dynamic contrast agent flow, and significantly improves reconstruction quality. Our model is trained by minimizing the discrepancy between synthesized projections and real captured DSA images. We further employ two training strategies to improve reconstruction quality: (1) coarse-to-fine progressive training for better geometry and (2) temporal perturbed rendering loss for temporal consistency. Experimental results have demonstrated high-quality 3D vessel reconstruction and 2D DSA image synthesis.
Zhentao Liu, Huangxuan Zhao, Wenhui Qin +7
School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China · National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China · School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China +1
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.
Jian Lin, Jiancheng Fang, Shaoyu Wang +4
School of Information Engineering, Nanchang University, Nanchang 330031, China · Laboratory of Image Science and Technology, the School of Computer Science and Engineering, and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing 210096, China
Arbitrary-Scale Super-Resolution (ASR) aims to reconstruct high-resolution images at any continuous magnification. While 2D Gaussian Splatting (GS) has recently shown great promise for ASR, current methods struggle to balance visual quality and computational cost. Approaches targeting high fidelity rely on powerful backbones and uniform, highly dense Gaussian grids, leading to prohibitive memory and inference costs. Conversely, methods prioritizing efficiency aggressively simplify their architectures, severely compromising visual quality. To bridge this gap, we observe that a core capability of GS remains largely underexplored in ASR: the potential for dynamic densification, i.e., the spatially adaptive allocation of Gaussians based on image content. Unlike standard scene fitting, where densification is guided by a known ground truth, applying this to ASR is highly non-trivial because the high-resolution target is exactly what the model must predict. To address this challenge, we propose QuADA-GS, an approach that retains a powerful representational backbone but autonomously predicts where to allocate Gaussians relying strictly on the low-resolution input. By adopting a sparse approach, QuADA-GS refines features and increases Gaussian density strictly where structural complexity demands it. Because this adaptive allocation produces a non-uniform hierarchical topology, we introduce a novel, highly efficient communication mechanism to process these sparse features, bypassing standard dense bottlenecks. Extensive experiments indicate that our approach successfully balances visual quality and computational requirements, providing an improved and competitive trade-off for ASR.
Giulio Federico, Giuseppe Amato, Claudio Gennaro +2
University of Pisa, Pisa, Italy · ISTI-CNR, Pisa, Italy