Single Image Reflection Removal via inter-layer Complementarity

• URL: http://arxiv.org/abs/2505.12641v1
• Date: Mon, 19 May 2025 02:50:15 GMT
• Title: Single Image Reflection Removal via inter-layer Complementarity
• Authors: Yue Huang, Zi'ang Li, Tianle Hu, Jie Wen, Guanbin Li, Jinglin Zhang, Guoxu Zhou, Xiaozhao Fang,
• Abstract summary: We introduce a novel inter-layer complementarity model and an efficient inter-layer complementarity attention mechanism for dual-stream architectures.<n>Our method achieves state-of-the-art separation quality on multiple public datasets while significantly reducing both computational cost and model complexity.
• Score: 63.37693451363996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although dual-stream architectures have achieved remarkable success in single image reflection removal, they fail to fully exploit inter-layer complementarity in their physical modeling and network design, which limits the quality of image separation. To address this fundamental limitation, we propose two targeted improvements to enhance dual-stream architectures: First, we introduce a novel inter-layer complementarity model where low-frequency components extracted from the residual layer interact with the transmission layer through dual-stream architecture to enhance inter-layer complementarity. Meanwhile, high-frequency components from the residual layer provide inverse modulation to both streams, improving the detail quality of the transmission layer. Second, we propose an efficient inter-layer complementarity attention mechanism which first cross-reorganizes dual streams at the channel level to obtain reorganized streams with inter-layer complementary structures, then performs attention computation on the reorganized streams to achieve better inter-layer separation, and finally restores the original stream structure for output. Experimental results demonstrate that our method achieves state-of-the-art separation quality on multiple public datasets while significantly reducing both computational cost and model complexity.

Related papers

• Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement [22.353926184394002]
  Single-scale feature extraction can match or surpass the performance of multi-scale methods.<n>SSD-Net combines CNN's local feature extraction capabilities with Transformer's global modeling strengths.
  arXiv  Detail & Related papers  (2025-08-06T06:41:58Z)
• Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification [7.4334395431083715]
  We propose the Hierarchical Mask-enhanced Dual Reconstruction Network (HMDRN) to improve fine-grained classification.<n>HMDRN incorporates a dual-layer feature reconstruction and fusion module that leverages complementary visual information from different network hierarchies.<n> experiments on three challenging fine-grained datasets demonstrate that HDRN consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-25T09:15:59Z)
• EchoIR: Advancing Image Restoration with Echo Upsampling and Bi-Level Optimization [0.0]
  We introduce the EchoIR, an UNet-like image restoration network with a bilateral learnable upsampling mechanism to bridge this gap.<n>In pursuit of modeling a hierarchical model of image restoration and upsampling tasks, we propose the Approximated Sequential Bi-level Optimization (AS-BLO)
  arXiv  Detail & Related papers  (2024-12-10T06:27:08Z)
• Blind Underwater Image Restoration using Co-Operational Regressor Networks [15.853520058218042]
  We propose a novel machine learning model, Co-Operational Regressor Networks (CoRe-Nets)<n>A CoRe-Net consists of two co-operating networks: the Apprentice Regressor (AR), responsible for image transformation, and the Master Regressor (MR), which evaluates the Peak Signal-to-Noise Ratio (PSNR) of the images generated by the AR and feeds it back to AR.<n>Our results and the optimized PyTorch implementation of the proposed approach are now publicly shared on GitHub.
  arXiv  Detail & Related papers  (2024-12-05T09:15:21Z)
• A Hybrid Transformer-Mamba Network for Single Image Deraining [70.64069487982916]
  Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions. We introduce a novel dual-branch hybrid Transformer-Mamba network, denoted as TransMamba, aimed at effectively capturing long-range rain-related dependencies.
  arXiv  Detail & Related papers  (2024-08-31T10:03:19Z)
• IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions [26.09373405194564]
  We present an efficient image processing transformer architecture with hierarchical attentions, called IPTV2. We adopt a focal context self-attention (FCSA) and a global grid self-attention (GGSA) to obtain adequate token interactions in local and global receptive fields. Our proposed IPT-V2 achieves state-of-the-art results on various image processing tasks, covering denoising, deblurring, deraining and obtains much better trade-off for performance and computational complexity than previous methods.
  arXiv  Detail & Related papers  (2024-03-31T10:01:20Z)
• Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing [54.168567276280505]
  We propose a novel Mutual Information-driven Triple interaction Network (MITNet) for image dehazing. The first stage, named amplitude-guided haze removal, aims to recover the amplitude spectrum of the hazy images for haze removal. The second stage, named phase-guided structure refined, devotes to learning the transformation and refinement of the phase spectrum.
  arXiv  Detail & Related papers  (2023-08-14T08:23:58Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• Learning to See Through Obstructions with Layered Decomposition [117.77024641706451]
  We present a learning-based approach for removing unwanted obstructions from moving images. Our method leverages motion differences between the background and obstructing elements to recover both layers. We show that the proposed approach learned from synthetically generated data performs well to real images.
  arXiv  Detail & Related papers  (2020-08-11T17:59:31Z)

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.