# SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency

arXiv: https://arxiv.org/abs/2303.07033 · HTML: https://mlsanity.com/paper/2303.07033/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 63 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2108.05565/) (2021)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [Unified Vision and Language Prompt Learning](https://mlsanity.com/paper/2210.07225/) (2022)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder](https://mlsanity.com/paper/2205.06803/) (2022)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation](https://mlsanity.com/paper/2212.04145/) (2022)
- [RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2201.06374/) (2022)

## Built on by (most cited first, 24 of 24)

- [Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing](https://mlsanity.com/paper/2403.01105/) (2024)
- [Understanding Layer Significance in LLM Alignment](https://mlsanity.com/paper/2410.17875/) (2024)
- [Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration](https://mlsanity.com/paper/2404.00288/) (2024)
- [Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal](https://mlsanity.com/paper/2407.16957/) (2024)
- [PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal](https://mlsanity.com/paper/2402.02374/) (2024)
- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer](https://mlsanity.com/paper/2404.13640/) (2024)
- [Intra and Inter Parser-Prompted Transformers for Effective Image Restoration](https://mlsanity.com/paper/2503.14037/) (2025)
- [Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks](https://mlsanity.com/paper/2406.00721/) (2024)
- [Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement](https://mlsanity.com/paper/2603.00853/) (2026)
- [Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey](https://mlsanity.com/paper/2505.16161/) (2025)
- [Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal](https://mlsanity.com/paper/2503.09013/) (2025)
- [Adaptive Blind All-in-One Image Restoration](https://mlsanity.com/paper/2411.18412/) (2024)
- [UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing](https://mlsanity.com/paper/2601.06909/) (2026)
- [Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration](https://mlsanity.com/paper/2409.03455/) (2024)
- [NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather](https://mlsanity.com/paper/2603.27228/) (2026)
- [Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance](https://mlsanity.com/paper/2605.22423/) (2026)
- [How Powerful Potential of Attention on Image Restoration?](https://mlsanity.com/paper/2403.10336/) (2024)
- [CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations](https://mlsanity.com/paper/2403.11220/) (2024)
- [SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal](https://mlsanity.com/paper/2409.19679/) (2024)
- [ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing](https://mlsanity.com/paper/2503.17488/) (2025)
- [Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal](https://mlsanity.com/paper/2608.06939/) (2026)
- [Can Large Pretrained Depth Estimation Models Help With Image Dehazing?](https://mlsanity.com/paper/2508.00698/) (2025)
- [Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation](https://mlsanity.com/paper/2608.20263/) (2026)

## Abstract (arXiv)

This work presents an effective depth-consistency self-prompt Transformer for image dehazing. It is motivated by an observation that the estimated depths of an image with haze residuals and its clear counterpart vary. Enforcing the depth consistency of dehazed images with clear ones, therefore, is essential for dehazing. For this purpose, we develop a prompt based on the features of depth differences between the hazy input images and corresponding clear counterparts that can guide dehazing models for better restoration. Specifically, we first apply deep features extracted from the input images to the depth difference features for generating the prompt that contains the haze residual information in the input. Then we propose a prompt embedding module that is designed to perceive the haze residuals, by linearly adding the prompt to the deep features. Further, we develop an effective prompt attention module to pay more attention to haze residuals for better removal. By incorporating the prompt, prompt embedding, and prompt attention into an encoder-decoder network based on VQGAN, we can achieve better perception quality. As the depths of clear images are not available at inference, and the dehazed images with one-time feed-forward execution may still contain a portion of haze residuals, we propose a new continuous self-prompt inference that can iteratively correct the dehazing model towards better haze-free image generation. Extensive experiments show that our method performs favorably against the state-of-the-art approaches on both synthetic and real-world datasets in terms of perception metrics including NIQE, PI, and PIQE.