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

arXiv: https://arxiv.org/abs/2405.15395 · HTML: https://mlsanity.com/paper/2405.15395/

## 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 (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [ViViD++: Vision for Visibility Dataset](https://mlsanity.com/paper/2204.06183/) (2022)
- [SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.03150/) (2021)
- [Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum](https://mlsanity.com/paper/1902.10892/) (2019)
- [TRansPose: Large-Scale Multispectral Dataset for Transparent Object](https://mlsanity.com/paper/2307.05016/) (2023)
- [Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception](https://mlsanity.com/paper/2401.13853/) (2024)
- [Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motion](https://mlsanity.com/paper/2201.04387/) (2022)
- [Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks](https://mlsanity.com/paper/2104.07196/) (2021)
- [WiSARD: A Labeled Visual and Thermal Image Dataset for Wilderness Search and Rescue](https://mlsanity.com/paper/2309.04453/) (2023)
- [Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras](https://mlsanity.com/paper/2012.14292/) (2020)
- [Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation](https://mlsanity.com/paper/2211.00960/) (2022)
- [Pixel-Wise Motion Deblurring of Thermal Videos](https://mlsanity.com/paper/2006.04973/) (2020)
- [Edge-based Monocular Thermal-Inertial Odometry in Visually Degraded Environments](https://mlsanity.com/paper/2210.10033/) (2022)
- [Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry](https://mlsanity.com/paper/2209.06588/) (2022)
- [Joint tone mapping and denoising of thermal infrared images via multi-scale Retinex and multi-task learning](https://mlsanity.com/paper/2305.00691/) (2023)

## Built on by (most cited first, 8 of 8)

- [Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges](https://mlsanity.com/paper/2503.22060/) (2025)
- [Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images](https://mlsanity.com/paper/2410.18340/) (2024)
- [RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments](https://mlsanity.com/paper/2503.04821/) (2025)
- [TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization](https://mlsanity.com/paper/2508.03727/) (2025)
- [Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement](https://mlsanity.com/paper/2506.23353/) (2025)
- [PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency](https://mlsanity.com/paper/2604.01791/) (2026)
- [TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index](https://mlsanity.com/paper/2606.19813/) (2026)
- [Aligned Radiometric RGB-Thermal Fusion for UAV Facade Anomaly Screening](https://mlsanity.com/paper/2609.12521/) (2026)

## 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