3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 2 Mar 2026.
Builds on
24 of 47 references.
References · 24
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
- 2017Deep Image Priorcited by 1,097
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
- 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
- 2023WIRE: Wavelet Implicit Neural Representationscited by 220
- 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 130
- 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 129
- 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
- 2022NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstructioncited by 106
12 more
- 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
- 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstructioncited by 73
- 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 65
- 2023Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Modelscited by 53
- 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
- 2020Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximationcited by 39
- 2018Seismic Signal Denoising and Decomposition Using Deep Neural Networkscited by 21
- 2024DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstructioncited by 13
- 2014Modular proximal optimization for multidimensional total-variation regularizationcited by 10
- 2020Field of Junctions: Extracting Boundary Structure at Low SNRcited by 6
- 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6
- 2024Geometric Algebra Planes: Convex Implicit Neural Volumescited by 5
Built on by
Not cited yet.