mlsanityData to 7 Oct 2026

MS-Glance: Bio-Insipred Non-semantic Context Vectors and their Applications in Supervising Image Reconstruction

arXiv 2410.23577 ↗First posted 31 Oct 2024eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Non-semantic context information is crucial for visual recognition, as the human visual perception system first uses global statistics to process scenes rapidly before identifying specific objects. However, while semantic information is increasingly incorporated into computer vision tasks such as image reconstruction, non-semantic information, such as global spatial structures, is often overlooked. To bridge the gap, we propose a biologically informed non-semantic context descriptor, MS-Glance, along with the Glance Index Measure for comparing two images. A Global Glance vector is formulated by randomly retrieving pixels based on a perception-driven rule from an image to form a vector representing non-semantic global context, while a local Glance vector is a flattened local image window, mimicking a zoom-in observation. The Glance Index is defined as the inner product of two standardized sets of Glance vectors. We evaluate the effectiveness of incorporating Glance supervision in two reconstruction tasks: image fitting with implicit neural representation (INR) and undersampled MRI reconstruction. Extensive experimental results show that MS-Glance outperforms existing image restoration losses across both natural and medical images. The code is available at urlhttps://github.com/Z7Gao/MSGlance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 88 references that are in the map. First posted on arXiv 31 Oct 2024.

Builds on

45 of 88 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  11. 2021Score-based diffusion models for accelerated MRIcited by 308
  12. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
33 more
  1. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  2. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  3. 2021COIN: COmpression with Implicit Neural representationscited by 232
  4. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  5. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  6. 2021Implicit Neural Representations for Image Compressioncited by 161
  7. 2018Deep Learning for Single Image Super-Resolution: A Brief Reviewcited by 158
  8. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 117
  9. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  10. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  11. 2017Deep learning for undersampled MRI reconstructioncited by 91
  12. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  13. 2017A Deep Cascade of Convolutional Neural Networks for MR Image Reconstructioncited by 74
  14. 2020DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Priorcited by 72
  15. 2022Towards performant and reliable undersampled MR reconstruction via diffusion model samplingcited by 59
  16. 2022Swin Transformer for Fast MRIcited by 56
  17. 2019Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisitioncited by 55
  18. 2022High-Frequency Space Diffusion Models for Accelerated MRIcited by 41
  19. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Modelscited by 37
  20. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
  21. 2023S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fieldscited by 25
  22. 2019Model Learning: Primal Dual Networks for Fast MR imagingcited by 22
  23. 2019i-RIM applied to the fastMRI challengecited by 16
  24. 2022Single Image Super-Resolution via a Dual Interactive Implicit Neural Networkcited by 15
  25. 2023SMRD: SURE-based Robust MRI Reconstruction with Diffusion Modelscited by 15
  26. 2023Correlated and Multi-frequency Diffusion Modeling for Highly Under-sampled MRI Reconstructioncited by 14
  27. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?cited by 11
  28. 2023Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imagingcited by 10
  29. 2020Deep Residual Dense U-Net for Resolution Enhancement in Accelerated MRI Acquisitioncited by 9
  30. 2024PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRIcited by 8
  31. 2018A Segmentation-aware Deep Fusion Network for Compressed Sensing MRIcited by 7
  32. 2024MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion modelcited by 3
  33. 2021Joint Calibrationless Reconstruction and Segmentation of Parallel MRIcited by 1

Built on by

Not cited yet.