3D 立体接点场：一种噪声鲁棒、无需训练的结构先验用于体积分量逆问题
3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
AI总结：
本文提出3D FoJ方法，通过优化3D楔形接点来实现体积分量逆问题的去噪，无需训练数据，保留和增强3D边缘和角结构，适用于低信噪比下的多种3D成像任务。
摘要：
体积分量去噪是计算成像中的基础问题，因为许多3D成像逆问题面临高水平的测量噪声。受Field of Junctions在2D图像去噪中的强大性能启发，我们提出了一种新颖的、完全体积分量的3D Field of Junctions（3D FoJ）表示方法，该方法优化了能够最好解释完整体积分量中每个3D块的3D楔形接点，同时鼓励重叠块之间的一致性。除了直接的体积分量去噪外，我们还利用3D FoJ作为结构先验，要求无训练数据，从而避免幻觉风险，保留和增强3D中的锐利边缘和角结构，即使在低信噪比（SNR）下也能保持，且可作为投影或近似梯度下降的去噪表示用于任何低SNR的体积分量逆问题。我们展示了3D FoJ在三种多样化的3D成像任务中成功实现体积分量重建和去噪：低剂量X射线计算机断层扫描（CT）、低温电子显微镜（cryo-ET）以及如激光雷达在恶劣天气下的点云去噪。在这些具有挑战性的低SNR体积分量成像问题中，3D FoJ优于评估的经典去噪器、未经训练的神经去噪器以及仅在噪声样例上训练的去噪器。代码可在https://github.com/voilalab/3D-Field-of-Junctions获取。
英文摘要：
Volume denoising is a foundational problem in computational imaging, as many 3D imaging inverse problems face high levels of measurement noise. Inspired by the strong 2D image denoising properties of Field of Junctions (ICCV 2021), we propose a novel, fully volumetric 3D Field of Junctions (3D FoJ) representation that optimizes a junction of 3D wedges that best explain each 3D patch of a full volume, while encouraging consistency between overlapping patches. In addition to direct volume denoising, we leverage our 3D FoJ representation as a structural prior that: (i) requires no training data, and thus precludes the risk of hallucination, (ii) preserves and enhances sharp edge and corner structures in 3D, even under low signal to noise ratio (SNR), and (iii) can be used as a drop-in denoising representation via projected or proximal gradient descent for any volumetric inverse problem with low SNR. We demonstrate successful volume reconstruction and denoising with 3D FoJ across three diverse 3D imaging tasks with low-SNR measurements: low-dose X-ray computed tomography (CT), cryogenic electron tomography (cryo-ET), and denoising point clouds such as those from lidar in adverse weather. Across these challenging low-SNR volumetric imaging problems, 3D FoJ outperforms the evaluated classical denoisers, untrained neural denoisers, and denoisers trained only on noisy examples. Code is available at https://github.com/voilalab/3D-Field-of-Junctions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
