mlsanityData to 7 Oct 2026

NeAT: Neural Adaptive Tomography

arXiv 2202.02171 ↗First posted 4 Feb 2022cs.CV cs.GR eess.IVcited by 11

Not on the map. Why?

Abstract (arXiv)

In this paper, we present Neural Adaptive Tomography (NeAT), the first adaptive, hierarchical neural rendering pipeline for multi-view inverse rendering. Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods. The adaptive explicit representation improves efficiency by facilitating empty space culling and concentrating samples in complex regions, while the neural features act as a neural regularizer for the 3D reconstruction. The NeAT framework is designed specifically for the tomographic setting, which consists only of semi-transparent volumetric scenes instead of opaque objects. In this setting, NeAT outperforms the quality of existing optimization-based tomography solvers while being substantially faster.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 35 of its 77 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

35 of 77 references.

References · 35

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
23 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  2. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  3. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  4. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  5. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  6. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  7. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  8. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  9. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  10. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  11. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  12. 2017Learned Primal-dual Reconstructioncited by 251
  13. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  14. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  15. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  16. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  17. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  18. 2018Radon Inversion via Deep Learningcited by 35
  19. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  20. 2020Implicit Feature Networks for Texture Completion from Partial 3D Datacited by 31
  21. 2019TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networkscited by 25
  22. 2020ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learningcited by 9
  23. 2017Scale-Space Anisotropic Total Variation for Limited Angle Tomographycited by 7

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 7; 2024: 1.

11 papers.

  1. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  2. 2022DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstructioncited by 73
  3. 2024Advances in 3D Generation: A Surveycited by 62
  4. 2023Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstructioncited by 42
  5. 2023VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Renderingcited by 14
  6. 2023Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reductioncited by 9
  7. 2022Gradient-Based Geometry Learning for Fan-Beam CT Reconstructioncited by 8
  8. 2023NeRFs: The Search for the Best 3D Representationcited by 7
  9. 2023TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstructioncited by 5
  10. 2022Neural Adaptive SCEne Tracingcited by 1
  11. 2023Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objectscited by 0