Metraipolis › archive › dc_c319fb356ea0

LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting — arXiv:2609.22849

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22849
License (as archived)
CC0-1.0
Archived
2026-10-09T21:59:18.937Z
SHA-256 of the archived text
84e3d41c49056ab86b108a986bb33bf652878a8e96cde99f24ca9b4bbfd0af84
Stable URL of this page
https://metraipolis.com/documento/dc_c319fb356ea0

How to cite

LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting — arXiv:2609.22849 — arXiv (en), https://arxiv.org/abs/2609.22849 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c319fb356ea0 (Metraipolis archive dc_c319fb356ea0, sha256 84e3d41c49056ab86b108a986bb33bf652878a8e96cde99f24ca9b4bbfd0af84)
BibTeX
@misc{dcc319fb356ea0,
  title = {LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting — arXiv:2609.22849},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22849},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c319fb356ea0; sha256 84e3d41c49056ab86b108a986bb33bf652878a8e96cde99f24ca9b4bbfd0af84},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22849. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In novel view synthesis and Computed Tomography (CT) reconstruction with sparse-view X-ray imaging, insufficient angular coverage leads to structural ambiguity and accumulated noise. Integrating 3D Gaussian Splatting (3DGS) with X-ray absorption physics can achieve promising results, but it suffers from noisy initialization, positional insensitivity, and weak gradients in low-density regions. In this paper, we propose a unified Latent Initialization and Gradient Optimization (LINGO) framework to address these issues. LINGO combines latent mask-space initialization with dynamic gradient optimization to improve point cloud structural completeness while accelerating training. It constructs voxel-level 3D filters from X-ray masks to robustly suppress background noise and provide reliable geometric priors. By employing an adaptive voxel scaling strategy and dynamically scaling loss, LINGO can adjust spatial resolution and explicitly amplify gradients in low-density structures. To evaluate the quality of initialization, we introduce the Initialization Point Cloud Structural Deviation (IPSD) metric. Experiments on the X3D dataset indicate that for the novel view synthesis task, LINGO improves the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) by an average of 0.72 and 0.0039, respectively, over baselines under identical sparse-view settings, achieving comparable reconstruction quality within 5k steps to state-of-the-art models typically trained with 30k iterations. For the CT reconstruction task, LINGO also demonstrates consistent improvements, with average PSNR and SSIM gains of 0.36 and 0.0134. These results highlight LINGO's effectiveness in both accelerating training and enhancing reconstruction quality across different sparse-view imaging scenarios.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.22849 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T21:45:20.820Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).