HazeCLIP: Towards Language Guided Real-World Image Dehazing

• URL: http://arxiv.org/abs/2407.13719v2
• Date: Fri, 10 Jan 2025 10:00:58 GMT
• Title: HazeCLIP: Towards Language Guided Real-World Image Dehazing
• Authors: Ruiyi Wang, Wenhao Li, Xiaohong Liu, Chunyi Li, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai,
• Abstract summary: Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks.
• Score: 62.4454483961341
• License:
• Abstract: Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. However, they often struggle with real-world hazy images due to domain shift, limiting their practical applicability. This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks. Inspired by the Contrastive Language-Image Pre-training (CLIP) model's ability to distinguish between hazy and clean images, we leverage it to evaluate dehazing results. Combined with a region-specific dehazing technique and tailored prompt sets, the CLIP model accurately identifies hazy areas, providing a high-quality, human-like prior that guides the fine-tuning process of pre-trained networks. Extensive experiments demonstrate that HazeCLIP achieves state-of-the-art performance in real-word image dehazing, evaluated through both visual quality and image quality assessment metrics. Codes are available at https://github.com/Troivyn/HazeCLIP.

Related papers

• CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP [19.80268944768578]
  Blind dehazed image quality assessment (BDQA) aims to accurately predict the visual quality of dehazed images without any reference information. We propose to adapt Contrastive Language-Image Pre-Training (CLIP), pre-trained on large-scale image-text pairs, to the BDQA task. We show that our proposed approach, named CLIP-DQA, achieves more accurate quality predictions over existing BDQA methods.
  arXiv  Detail & Related papers  (2025-02-03T14:12:25Z)
• Decoder Pre-Training with only Text for Scene Text Recognition [54.93037783663204]
  Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. We introduce a novel method named Decoder Pre-training with only text for STR (DPTR) DPTR treats text embeddings produced by the CLIP text encoder as pseudo visual embeddings and uses them to pre-train the decoder.
  arXiv  Detail & Related papers  (2024-08-11T06:36:42Z)
• Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities [88.398085358514]
  Contrastive Deepfake Embeddings (CoDE) is a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities.
  arXiv  Detail & Related papers  (2024-07-29T18:00:10Z)
• Creating Realistic Anterior Segment Optical Coherence Tomography Images using Generative Adversarial Networks [0.0]
  Generative Adversarial Network (GAN) purposed to create high-resolution, realistic Anterior Segment Optical Coherence Tomography (AS- OCT) images. We trained the Style and WAvelet based GAN on 142,628 AS- OCT B-scans.
  arXiv  Detail & Related papers  (2023-06-24T20:48:00Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)
• UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning [57.40713083410888]
  This paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. We conduct comprehensive experiments to evaluate our UCL-Dehaze and demonstrate its superiority over the state-of-the-arts.
  arXiv  Detail & Related papers  (2022-05-04T03:25:13Z)
• Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle [7.452382358080454]
  We propose a mutual learning dehazing framework for domain adaption. Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain. We show that the framework outperforms state-of-the-art dehazing techniques in terms of subjective and objective evaluation.
  arXiv  Detail & Related papers  (2022-03-17T16:32:14Z)
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [91.56988987393483]
  We present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones.
  arXiv  Detail & Related papers  (2021-12-02T18:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.