mlsanityData to 7 Oct 2026

Dual-branch Graph Feature Learning for NLOS Imaging

arXiv 2502.19683 ↗First posted 27 Feb 2025eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems face several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, which restricts practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyperparameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces the innovative methodology, xnet, which integrates an albedo-focused reconstruction branch dedicated to albedo information recovery and a depth-focused reconstruction branch that extracts geometrical structure, to overcome these obstacles. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. To our knowledge, we are the first to employ the GNN as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. Comprehensive experiments demonstrate that our method attains the highest level of performance among existing methods across synthetic and real data. https://github.com/Nicholassu/DG-NLOS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 51 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

24 of 51 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  11. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  12. 2020Distilling Knowledge from Graph Convolutional Networkscited by 128
12 more
  1. 2019Orthogonal Convolutional Neural Networkscited by 122
  2. 2018Virtual Wave Optics for Non-Line-of-Sight Imagingcited by 54
  3. 2020Non-line-of-sight Imagingcited by 41
  4. 2021Non-line-of-Sight Imaging via Neural Transient Fieldscited by 41
  5. 2019Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radarcited by 40
  6. 2021Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imagingcited by 31
  7. 2021S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representationcited by 23
  8. 2020Deep Non-Line-of-Sight Reconstructioncited by 21
  9. 2020Real-time Non-line-of-Sight imaging of dynamic scenescited by 20
  10. 2019Recent Advances in Imaging Around Cornerscited by 17
  11. 2023NLOS-NeuS: Non-line-of-sight Neural Implicit Surfacecited by 13
  12. 2022Non-line-of-sight imaging with arbitrary illumination and detection patterncited by 10

Built on by

Not cited yet.