3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems

• URL: http://arxiv.org/abs/2603.02149v1
• Date: Mon, 02 Mar 2026 18:11:59 GMT
• Title: 3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
• Abstract summary: Many 3D imaging inverse problems face high levels of measurement noise.<n>We propose a novel, fully volumetric 3D Field of Junctions representation.<n>We demonstrate successful volume reconstruction and denoising with 3D FoJ across three diverse 3D imaging tasks.
• Score: 8.98577835141982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 a mixture of classical and neural methods.

Related papers

• High Volume Rate 3D Ultrasound Reconstruction with Diffusion Models [14.007660129016852]
  Three-dimensional ultrasound enables real-time volumetric visualization of anatomical structures.<n> achieving both high volume rates and high image quality remains a significant challenge.<n>This paper introduces a novel approach to 3D ultrasound reconstruction by employing diffusion models (DMs) to achieve increased spatial and temporal resolution.
  arXiv  Detail & Related papers  (2025-05-28T08:14:12Z)
• V2V3D: View-to-View Denoised 3D Reconstruction for Light-Field Microscopy [12.356249860549472]
  Light field microscopy (LFM) has gained significant attention due to its ability to capture snapshot-based, large-scale 3D fluorescence images.<n>Existing LFM reconstruction algorithms are highly sensitive to sensor noise or require hard-to-get ground-truth annotated data for training.<n>This paper introduces V2V3D, an unsupervised view2view-based framework that establishes a new paradigm for joint optimization of image denoising and 3D reconstruction.
  arXiv  Detail & Related papers  (2025-04-10T15:29:26Z)
• SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis [59.73403876485574]
  We propose SuperNeRF-GAN, a universal framework for 3D-consistent super-resolution.<n>A key highlight of SuperNeRF-GAN is its seamless integration with NeRF-based 3D-aware image synthesis methods.<n> Experimental results demonstrate the superior efficiency, 3D-consistency, and quality of our approach.
  arXiv  Detail & Related papers  (2025-01-12T10:31:33Z)
• 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.<n>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)
• A Refined 3D Gaussian Representation for High-Quality Dynamic Scene Reconstruction [2.022451212187598]
  In recent years, Neural Radiance Fields (NeRF) has revolutionized three-dimensional (3D) reconstruction with its implicit representation. 3D Gaussian Splatting (3D-GS) has departed from the implicit representation of neural networks and instead directly represents scenes as point clouds with Gaussian-shaped distributions. This paper purposes a refined 3D Gaussian representation for high-quality dynamic scene reconstruction. Experimental results demonstrate that our method surpasses existing approaches in rendering quality and speed, while significantly reducing the memory usage associated with 3D-GS.
  arXiv  Detail & Related papers  (2024-05-28T07:12:22Z)
• N-BVH: Neural ray queries with bounding volume hierarchies [51.430495562430565]
  In 3D computer graphics, the bulk of a scene's memory usage is due to polygons and textures. We devise N-BVH, a neural compression architecture designed to answer arbitrary ray queries in 3D. Our method provides faithful approximations of visibility, depth, and appearance attributes.
  arXiv  Detail & Related papers  (2024-05-25T13:54:34Z)
• MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections [27.684664614389316]
  MicroDiffusion is a pioneering tool facilitating high-quality, depth-resolved 3D volume reconstruction. We pretrain an INR model to transform 2D axially-projected images into a preliminary 3D volume. By conditioning the diffusion model on the closest 2D projection, MicroDiffusion substantially enhances fidelity in resulting 3D reconstructions.
  arXiv  Detail & Related papers  (2024-03-16T05:22:16Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• The Impact of Loss Functions and Scene Representations for 3D/2D Registration on Single-view Fluoroscopic X-ray Pose Estimation [1.758213853394712]
  We first develop a differentiable projection rendering framework for the efficient computation of Digitally Reconstructed Radiographs (DRRs) We then perform pose estimation by iterative descent using various candidate loss functions, that quantify the image discrepancy of the synthesized DRR with respect to the ground-truth fluoroscopic X-ray image. Using the Mutual Information loss, a comprehensive evaluation of pose estimation performed on a tomographic X-ray dataset of 50 patients$'$ skulls shows that utilizing either discretized (CBCT) or neural (NeTT/mNeRF) scene representations in DiffProj leads to
  arXiv  Detail & Related papers  (2023-08-01T01:12:29Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)
• NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion [107.67277084886929]
  Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. We propose NerfDiff, which addresses this issue by distilling the knowledge of a 3D-aware conditional diffusion model (CDM) into NeRF through synthesizing and refining a set of virtual views at test time. We further propose a novel NeRF-guided distillation algorithm that simultaneously generates 3D consistent virtual views from the CDM samples, and finetunes the NeRF based on the improved virtual views.
  arXiv  Detail & Related papers  (2023-02-20T17:12:00Z)

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.