mlsanityData to 14 Oct 2026

Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image

arXiv 2405.15395 ↗First posted 24 May 2024cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Thermal infrared (TIR) cameras are emerging as promising sensors in safety-related fields due to their robustness against external illumination. However, RAW TIR image has 14 bits of pixel depth and needs to be rescaled into 8 bits for general applications. Previous works utilize a global 1D look-up table to compute pixel-wise gain solely based on its intensity, which degrades image quality by failing to consider the local nature of the heat. We propose Fieldscale, a rescaling based on locality-aware 2D fields where both the intensity value and spatial context of each pixel within an image are embedded. It can adaptively determine the pixel gain for each region and produce spatially consistent 8-bit rescaled images with minimal information loss and high visibility. Consistent performance improvement on image quality assessment and two other downstream tasks support the effectiveness and usability of Fieldscale. All the codes are publicly opened to facilitate research advancements in this field. https://github.com/hyeonjaegil/fieldscale

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

26 of 45 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  5. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  6. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  7. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  8. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  9. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  10. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  11. 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
  12. 2022Deep Visual Geo-localization Benchmarkcited by 84
14 more
  1. 2022ViViD++: Vision for Visibility Datasetcited by 34
  2. 2021SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Drivingcited by 23
  3. 2019Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrumcited by 22
  4. 2023TRansPose: Large-Scale Multispectral Dataset for Transparent Objectcited by 15
  5. 2024Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perceptioncited by 15
  6. 2022Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motioncited by 14
  7. 2021Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networkscited by 12
  8. 2023WiSARD: A Labeled Visual and Thermal Image Dataset for Wilderness Search and Rescuecited by 9
  9. 2020Online Photometric Calibration of Automatic Gain Thermal Infrared Camerascited by 6
  10. 2022Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulationcited by 6
  11. 2020Pixel-Wise Motion Deblurring of Thermal Videoscited by 5
  12. 2022Edge-based Monocular Thermal-Inertial Odometry in Visually Degraded Environmentscited by 5
  13. 2022Data-Efficient Collaborative Decentralized Thermal-Inertial Odometrycited by 4
  14. 2023Joint tone mapping and denoising of thermal infrared images via multi-scale Retinex and multi-task learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.