DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction

• URL: http://arxiv.org/abs/2604.21518v1
• Date: Thu, 23 Apr 2026 10:27:54 GMT
• Title: DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
• Abstract summary: We propose DiffNR, a novel framework that enhances NR optimization with diffusion priors.<n>At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices.<n>In experiments, DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.
• Score: 42.4365911571903
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel framework that enhances NR optimization with diffusion priors. At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices. We integrate specialized conditioning layers into the network and develop tailored data curation strategies to support model finetuning. During reconstruction, SliceFixer periodically generates pseudo-reference volumes, providing auxiliary 3D perceptual supervision to fix underconstrained regions. Compared to prior methods that embed CT solvers into time-consuming iterative denoising, our repair-and-augment strategy avoids frequent diffusion model queries, leading to better runtime performance. Extensive experiments show that DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.

Related papers

• Wavelet-Optimized Pseudo-3D Accelerated Diffusion Model for Truncated Computed Laminography [12.168086376276934]
  Field-of-view (FOV) limitations inevitably lead to truncation of projected data.<n>Existing deep learning methods rely on 2D architectures that lack rigorous data consistency constraints.<n>We propose a novel wavelet-optimized pseudo-3D accelerated diffusion model for CL truncation reconstruction (CL-DM)
  arXiv  Detail & Related papers  (2026-06-30T08:24:57Z)
• Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography [11.284905409634957]
  We propose LADES, a ground-truth-free optimization controller for sparse-view Gaussian tomography.<n>Experiments on sparse-view CT reconstruction show that LADES improves volumetric fidelity, suppresses structural degeneration, and substantially reduces training time.
  arXiv  Detail & Related papers  (2026-06-21T14:24:02Z)
• Unrolled Reconstruction with Integrated Super-Resolution for Accelerated 3D LGE MRI [0.07026564887314535]
  We propose a hybrid unrolled reconstruction framework in which an Enhanced Deep Super-Resolution (EDSR) network replaces the operator within each iteration of the optimization loop.<n>Across acceleration factors, the proposed method consistently improves PSNR and SSIM over standard unrolled reconstruction.<n>These results demonstrate that integrating super-resolution priors directly within model-based reconstruction provides measurable gains in accelerated 3D LGE MRI.
  arXiv  Detail & Related papers  (2026-03-18T21:48:48Z)
• Optimizing 3D Diffusion Models for Medical Imaging via Multi-Scale Reward Learning [7.493047521402676]
  This paper presents a method to enhance 3D diffusion models using Reinforcement Learning (RL) with multi-scale feedback.<n>We fine-tune the model using Proximal Policy Optimization (PPO), guided by a novel reward system that integrates both 2D slice-wise assessments and 3D analysis.<n>Our results indicate that incorporating RL feedback effectively steers the generation process toward higher quality distributions.
  arXiv  Detail & Related papers  (2026-03-06T11:30:55Z)
• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting [63.138778159026934]
  We propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO.<n> ERGO dynamically estimates the view-specific excess risk and adaptively adjust loss weights during optimization.<n>Experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T20:44:43Z)
• Adaptive Training of INRs via Pruning and Densification [6.759337697337581]
  We introduce AIRe, an adaptive training scheme that refines the implicit neural representations over the course of optimization.<n>Our method uses a neuron pruning mechanism to avoid redundancy and input frequency densification to improve representation capacity.<n>Code and pretrained models will be released for public use.
  arXiv  Detail & Related papers  (2025-10-27T23:52:46Z)
• A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields [46.03878128080501]
  We propose to employ view-consistent distributions instead of fixed depth value estimations to regularize NeRF training.<n>By sampling from the view-consistency distributions, an implicit regularization is imposed on the training of NeRF.<n>We also utilize a depth-pushing loss that works in conjunction with the sampling technique to jointly provide effective regularizations for eliminating the failure modes.
  arXiv  Detail & Related papers  (2025-07-06T14:48:10Z)
• QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization [69.50126552763157]
  Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more.<n>Existing approaches based on rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model textureless regions.<n>We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes.
  arXiv  Detail & Related papers  (2025-05-08T18:43:26Z)
• DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes [81.56206845824572]
  Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. Few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.
  arXiv  Detail & Related papers  (2024-11-19T07:51:44Z)
• Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting [60.393072253444934]
  We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation.
  arXiv  Detail & Related papers  (2023-12-08T03:55:34Z)
• SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation [66.16525145765604]
  We introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud. Experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets.
  arXiv  Detail & Related papers  (2023-10-26T12:47:26Z)
• VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations [25.88881764546414]
  VQ-NeRF is an efficient pipeline for enhancing implicit neural representations via vector quantization. We present an innovative multi-scale NeRF sampling scheme that concurrently optimize the NeRF model at both compressed and original scales. We incorporate a semantic loss function to improve the geometric fidelity and semantic coherence of our 3D reconstructions.
  arXiv  Detail & Related papers  (2023-10-23T01:41:38Z)

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.