# TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement

arXiv: https://arxiv.org/abs/2503.08168 · HTML: https://mlsanity.com/paper/2503.08168/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 80 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network](https://mlsanity.com/paper/2106.14501/) (2021)
- [Global Structure-Aware Diffusion Process for Low-Light Image Enhancement](https://mlsanity.com/paper/2310.17577/) (2023)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement](https://mlsanity.com/paper/2405.03349/) (2024)
- [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020)
- [CLE Diffusion: Controllable Light Enhancement Diffusion Model](https://mlsanity.com/paper/2308.06725/) (2023)
- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion](https://mlsanity.com/paper/2501.04606/) (2025)

## Built on by (most cited first, 9 of 9)

- [FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction](https://mlsanity.com/paper/2506.21562/) (2025)
- [Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings](https://mlsanity.com/paper/2512.12492/) (2025)
- [FloorplanMAE:A self-supervised framework for complete floorplan generation from partial inputs](https://mlsanity.com/paper/2506.08363/) (2025)
- [Segment Any Architectural Facades (SAAF):An automatic segmentation model for building facades, walls and windows based on multimodal semantics guidance](https://mlsanity.com/paper/2506.09071/) (2025)
- [MARS: Memory-Enhanced Agents with Reflective Self-improvement](https://mlsanity.com/paper/2503.19271/) (2025)
- [ArchiLense: A Framework for Quantitative Analysis of Architectural Styles Based on Vision Large Language Models](https://mlsanity.com/paper/2506.07739/) (2025)
- [TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation](https://mlsanity.com/paper/2503.17669/) (2025)
- [UrbanSense:A Framework for Quantitative Analysis of Urban Streetscapes leveraging Vision Large Language Models](https://mlsanity.com/paper/2506.10342/) (2025)
- [ArchShapeNet:An Interpretable 3D-CNN Framework for Evaluating Architectural Shapes](https://mlsanity.com/paper/2506.14832/) (2025)

## Abstract (arXiv)

Deep learning-based image enhancement methods show significant advantages in reducing noise and improving visibility in low-light conditions. These methods are typically based on one-to-one mapping, where the model learns a direct transformation from low light to specific enhanced images. Therefore, these methods are inflexible as they do not allow highly personalized mapping, even though an individual's lighting preferences are inherently personalized. To overcome these limitations, we propose a new light enhancement task and a new framework that provides customized lighting control through prompt-driven, semantic-level, and quantitative brightness adjustments. The framework begins by leveraging a Large Language Model (LLM) to understand natural language prompts, enabling it to identify target objects for brightness adjustments. To localize these target objects, the Retinex-based Reasoning Segment (RRS) module generates precise target localization masks using reflection images. Subsequently, the Text-based Brightness Controllable (TBC) module adjusts brightness levels based on the generated illumination map. Finally, an Adaptive Contextual Compensation (ACC) module integrates multi-modal inputs and controls a conditional diffusion model to adjust the lighting, ensuring seamless and precise enhancements accurately. Experimental results on benchmark datasets demonstrate our framework's superior performance at increasing visibility, maintaining natural color balance, and amplifying fine details without creating artifacts. Furthermore, its robust generalization capabilities enable complex semantic-level lighting adjustments in diverse open-world environments through natural language interactions.