# LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion

arXiv: https://arxiv.org/abs/2405.10550 · HTML: https://mlsanity.com/paper/2405.10550/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 17 May 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [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)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps](https://mlsanity.com/paper/2305.15583/) (2023)
- [ISINet: An Instance-Based Approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2007.05533/) (2020)
- [Pyramid Diffusion Models For Low-light Image Enhancement](https://mlsanity.com/paper/2305.10028/) (2023)
- [Dual Illumination Estimation for Robust Exposure Correction](https://mlsanity.com/paper/1910.13688/) (2019)
- [CLE Diffusion: Controllable Light Enhancement Diffusion Model](https://mlsanity.com/paper/2308.06725/) (2023)
- [Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay](https://mlsanity.com/paper/2308.14100/) (2023)
- [Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art](https://mlsanity.com/paper/2304.13014/) (2023)
- [LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion](https://mlsanity.com/paper/2307.02452/) (2023)
- [The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior](https://mlsanity.com/paper/2304.11409/) (2023)
- [Speed up the inference of diffusion models via shortcut MCMC sampling](https://mlsanity.com/paper/2301.01206/) (2022)

## Built on by (most cited first, 12 of 12)

- [Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery](https://mlsanity.com/paper/2408.04958/) (2024)
- [Physics-Inspired Generative Models in Medical Imaging: A Review](https://mlsanity.com/paper/2407.10856/) (2024)
- [Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement](https://mlsanity.com/paper/2505.01766/) (2025)
- [Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting](https://mlsanity.com/paper/2506.23308/) (2025)
- [EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion](https://mlsanity.com/paper/2511.05873/) (2025)
- [Text2Traffic: A Text-to-Image Generation and Editing Method for Traffic Scenes](https://mlsanity.com/paper/2511.12932/) (2025)
- [SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement](https://mlsanity.com/paper/2507.02252/) (2025)
- [SPICE: Simple and Practical Image Clarification and Enhancement](https://mlsanity.com/paper/2510.08358/) (2025)
- [BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies](https://mlsanity.com/paper/2510.21000/) (2025)
- [PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal](https://mlsanity.com/paper/2603.22844/) (2026)
- [DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration](https://mlsanity.com/paper/2606.19097/) (2026)
- [On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos](https://mlsanity.com/paper/2608.14262/) (2026)

## Abstract (arXiv)

Advances in endoscopy use in surgeries face challenges like inadequate lighting. Deep learning, notably the Denoising Diffusion Probabilistic Model (DDPM), holds promise for low-light image enhancement in the medical field. However, DDPMs are computationally demanding and slow, limiting their practical medical applications. To bridge this gap, we propose a lightweight DDPM, dubbed LighTDiff. It adopts a T-shape model architecture to capture global structural information using low-resolution images and gradually recover the details in subsequent denoising steps. We further prone the model to significantly reduce the model size while retaining performance. While discarding certain downsampling operations to save parameters leads to instability and low efficiency in convergence during the training, we introduce a Temporal Light Unit (TLU), a plug-and-play module, for more stable training and better performance. TLU associates time steps with denoised image features, establishing temporal dependencies of the denoising steps and improving denoising outcomes. Moreover, while recovering images using the diffusion model, potential spectral shifts were noted. We further introduce a Chroma Balancer (CB) to mitigate this issue. Our LighTDiff outperforms many competitive LLIE methods with exceptional computational efficiency.