IET Computer Vision最新文献

Multi-Attention Fusion Artistic Radiance Fields and Beyond 多关注融合艺术光芒领域和超越

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-06-21 DOI: 10.1049/cvi2.70017

Qianru Chen, Yufan Zhou, Xintong Hou, Kunze Jiang, Jincheng Li, Chao Wu

{"title":"Multi-Attention Fusion Artistic Radiance Fields and Beyond","authors":"Qianru Chen, Yufan Zhou, Xintong Hou, Kunze Jiang, Jincheng Li, Chao Wu","doi":"10.1049/cvi2.70017","DOIUrl":"https://doi.org/10.1049/cvi2.70017","url":null,"abstract":"We present MRF (multi-attention fusion artistic radiance fields), a novel approach to 3D scene stylisation that synthesises artistic rendering by integrating stylised 2D images with neural radiance fields. Our method effectively incorporates high-frequency stylistic elements from 2D artistic representations while maintaining geometric consistency across multiple viewpoints. To address the challenges of view-dependent stylisation coherence and semantic fidelity, we introduce two key components: (1) a multi-scale attention module (MAM) that facilitates hierarchical feature extraction and fusion across different spatial resolutions and (2) a CLIP-guided semantic consistency module that preserves the underlying scene structure during style transfer. Through extensive experimentation, we demonstrate that MRF achieves superior stylisation quality and detail preservation compared to state-of-the-art methods, particularly in capturing fine artistic details while maintaining view consistency. Our approach represents a significant advancement in neural rendering-based artistic stylisation of 3D scenes.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70017","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PAD: Detail-Preserving Point Cloud Reconstruction and Generation via Autodecoders PAD：保留细节的点云重建和生成通过自动解码器

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-06-18 DOI: 10.1049/cvi2.70031

Yakai Zhang, Ping Yang, Haoran Wang, Zizhao Wu, Xiaoling Gu, Alexandru Telea, Kosinka Jiri

{"title":"PAD: Detail-Preserving Point Cloud Reconstruction and Generation via Autodecoders","authors":"Yakai Zhang, Ping Yang, Haoran Wang, Zizhao Wu, Xiaoling Gu, Alexandru Telea, Kosinka Jiri","doi":"10.1049/cvi2.70031","DOIUrl":"https://doi.org/10.1049/cvi2.70031","url":null,"abstract":"High-accuracy point cloud (self-) reconstruction is crucial for point cloud editing, translation, and unsupervised representation learning. However, existing point cloud reconstruction methods often sacrifice many geometric details. Altough many techniques have proposed how to construct better point cloud decoders, only a few have designed point cloud encoders from a reconstruction perspective. We propose an autodecoder architecture to achieve detail-preserving point cloud reconstruction while bypassing the performance bottleneck of the encoder. Our architecture is theoretically applicable to any existing point cloud decoder. For training, both the weights of the decoder and the pre-initialised latent codes, corresponding to the input points, are updated simultaneously. Experimental results demonstrate that our autodecoder achieves an average reduction of 24.62% in Chamfer Distance compared to existing methods, significantly improving reconstruction quality on the ShapeNet dataset. Furthermore, we verify the effectiveness of our autodecoder in point cloud generation, upsampling, and unsupervised representation learning to demonstrate its performance on downstream tasks, which is comparable to the state-of-the-art methods. We will make our code publicly available after peer review.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GRVT: Improving the Transferability of Adversarial Attacks Through Gradient Related Variance and Input Transformation GRVT：通过梯度相关方差和输入变换提高对抗性攻击的可转移性

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-06-11 DOI: 10.1049/cvi2.70034

Yanlei Wei, Xiaolin Zhang, Yongping Wang, Jingyu Wang, Lixin Liu

{"title":"GRVT: Improving the Transferability of Adversarial Attacks Through Gradient Related Variance and Input Transformation","authors":"Yanlei Wei, Xiaolin Zhang, Yongping Wang, Jingyu Wang, Lixin Liu","doi":"10.1049/cvi2.70034","DOIUrl":"https://doi.org/10.1049/cvi2.70034","url":null,"abstract":"As we all know, the emergence of a large number of adversarial samples reveals the vulnerability of deep neural networks. Attackers seriously affect the performance of models by adding imperceptible perturbations. Although adversarial samples have a high transferability success rate in white-box models, they are less effective in black-box models. To address this problem, this paper proposes a new transferability attack strategy, Gradient Related Variance and Input Transformation Attack (GRVT). First, the image is divided into small blocks, and random transformations are applied to each block to generate diversified images; then, in the gradient update process, the gradient of the neighbourhood area is introduced, and the current gradient is associated with the neighbourhood average gradient through Cosine Similarity. The current gradient direction is adjusted using the associated gradient combined with the previous gradient variance, and a step size reducer adjusts the gradient step size. Experiments on the ILSVRC 2012 dataset show that the transferability success rate of adversarial samples between convolutional neural network (CNN) and vision transformer (ViT) models is higher than that of currently advanced methods. Additionally, the adversarial samples generated on the ensemble model are practical against nine defence strategies. GRVT shows excellent transferability and broad applicability.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced Foreground–Background Discrimination for Weakly Supervised Semantic Segmentation 弱监督语义分割的增强前景背景判别

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-06-09 DOI: 10.1049/cvi2.70029

Zhoufeng Liu, Bingrui Li, Miao Yu, Guangshuai Gao, Chunlei Li

{"title":"Enhanced Foreground–Background Discrimination for Weakly Supervised Semantic Segmentation","authors":"Zhoufeng Liu, Bingrui Li, Miao Yu, Guangshuai Gao, Chunlei Li","doi":"10.1049/cvi2.70029","DOIUrl":"https://doi.org/10.1049/cvi2.70029","url":null,"abstract":"Weakly supervised semantic segmentation (WSSS) methods are extensively studied due to the availability of image-level annotations. Relying on class activation maps (CAMs) derived from original classification networks often suffers from issues such as inaccurate object localization, incomplete object regions, and the inclusion of confusing background pixels. To address these issues, we propose a two-stage method that enhances the foreground–background discriminative ability in a global context (FB-DGC). Specifically, a cross-domain feature calibration module (CFCM) is first proposed to calibrate foreground and background salient features using global spatial location information, thereby expanding foreground features while mitigating the impact of inaccurate localization in class activation regions. A class-specific distance module (CSDM) is further adopted to facilitate the separation of foreground–background features, thereby enhancing the activation of target regions, which alleviates the over-smoothing of features produced by the network and mitigates issues associated with confused features. In addition, an adaptive edge feature extraction (AEFE) strategy is proposed to identify target features in candidate boundary regions and capture missed features, compensating for drawbacks in recognising the co-occurrence of multiple targets. The proposed method is extensively evaluated on the challenging PASCAL VOC 2012 and MS COCO 2014 datasets, demonstrating its feasibility and superiority.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mamba4SOD: RGB-T Salient Object Detection Using Mamba-Based Fusion Module Mamba4SOD：基于mamba融合模块的RGB-T显著目标检测

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-06-05 DOI: 10.1049/cvi2.70033

Yi Xu, Ruichao Hou, Ziheng Qi, Tongwei Ren

引用次数: 0

Object Detection Based on CNN and Vision-Transformer: A Survey 基于CNN和视觉变换的目标检测研究进展

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-05-31 DOI: 10.1049/cvi2.70028

Jinfeng Cao, Bo Peng, Mingzhong Gao, Haichun Hao, Xinfang Li, Hongwei Mou

{"title":"Object Detection Based on CNN and Vision-Transformer: A Survey","authors":"Jinfeng Cao, Bo Peng, Mingzhong Gao, Haichun Hao, Xinfang Li, Hongwei Mou","doi":"10.1049/cvi2.70028","DOIUrl":"https://doi.org/10.1049/cvi2.70028","url":null,"abstract":"Object detection is the most crucial and challenging task of computer vision and has been used in various fields in recent years, such as autonomous driving and industrial inspection. Traditional object detection methods are mainly based on the sliding windows and the handcrafted features, which have problems such as insufficient understanding of image features and low accuracy of detection. With the rapid advancements in deep learning, convolutional neural networks (CNNs) and vision transformers have become fundamental components in object detection models. These components are capable of learning more advanced and deeper image properties, leading to a transformational breakthrough in the performance of object detection. In this review, we comprehensively review the representative object detection models from deep learning periods, tracing their architectural shifts and technological breakthroughs. Furthermore, we discuss key challenges and promising research directions in the object detection. This review aims to provide a comprehensive foundation for practitioners to enhance their understanding of object detection technologies.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FastVDT: Fast Transformer With Optimised Attention Masks and Positional Encoding for Visual Dialogue FastVDT：快速变压器与优化的注意力面具和位置编码的视觉对话

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-05-29 DOI: 10.1049/cvi2.70022

Qiangqiang He, Shuwei Qian, Chongjun Wang

{"title":"FastVDT: Fast Transformer With Optimised Attention Masks and Positional Encoding for Visual Dialogue","authors":"Qiangqiang He, Shuwei Qian, Chongjun Wang","doi":"10.1049/cvi2.70022","DOIUrl":"https://doi.org/10.1049/cvi2.70022","url":null,"abstract":"The visual dialogue task requires computers to comprehend image content and preceding question-and-answer history to accurately answer related questions, with each round of dialogue providing the necessary historical context for subsequent interactions. Existing research typically processes multiple questions related to a single image as independent samples, which results in redundant modelling of the images and their captions and substantially increases computational costs. To address the challenges above, we introduce a fast transformer for visual dialogue, termed FastVDT, which utilises novel attention masks and continuous positional encoding. FastVDT models multiple image-related questions as an integrated entity, accurately processing prior conversation history in each dialogue round while predicting answers to multiple questions. Our method effectively captures the interrelations among questions and significantly reduces computational overhead. Experimental results demonstrate that our method delivers outstanding performance on the VisDial v0.9 and v1.0 datasets. FastVDT achieves comparable performance to VD-BERT and VU-BERT while reducing computational costs by 80% and 56%, respectively.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70022","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

End-to-End Cascaded Image Restoration and Object Detection for Rain and Fog Conditions 雨和雾条件下的端到端级联图像恢复和目标检测

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-05-19 DOI: 10.1049/cvi2.70021

Peng Li, Jun Ni, Dapeng Tao

{"title":"End-to-End Cascaded Image Restoration and Object Detection for Rain and Fog Conditions","authors":"Peng Li, Jun Ni, Dapeng Tao","doi":"10.1049/cvi2.70021","DOIUrl":"https://doi.org/10.1049/cvi2.70021","url":null,"abstract":"Adverse weather conditions in real-world scenarios can degrade the performance of deep learning-based object detection models. A commonly used approach is to apply image restoration before object detection to improve degraded images. However, there is no direct correlation between the visual quality of image restoration and the object detection accuracy. Furthermore, image restoration and object detection have potential conflicting objectives, making joint optimisation difficult. To address this, we propose an end-to-end object detection network specifically designed for rainy and foggy conditions. Our approach cascades an image restoration subnetwork with a detection subnetwork and optimises them jointly through a shared objective. Specifically, we introduce an expanded dilated convolution block and a weather attention block to enhance the effectiveness and robustness of the restoration network under various weather degradations. Additionally, we incorporate an auxiliary alignment branch with feature alignment loss to align the features of restored and clean images within the detection backbone, enabling joint optimisation of both subnetworks. A novel training strategy is also proposed to further improve object detection performance under rainy and foggy conditions. Extensive experiments on the vehicle-rain-fog, VOC-fog and real-world fog datasets demonstrate that our method outperforms recent state-of-the-art approaches in image restoration quality and detection accuracy. The code is available at https://github.com/HappyPessimism/RainFog-Restoration-Detection.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70021","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144091874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LRCM: Enhancing Adversarial Purification Through Latent Representation Compression LRCM：通过潜在表征压缩增强对抗性纯化

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-05-19 DOI: 10.1049/cvi2.70030

Yixin Li, Xintao Luo, Weijie Wu, Minjia Zheng

{"title":"LRCM: Enhancing Adversarial Purification Through Latent Representation Compression","authors":"Yixin Li, Xintao Luo, Weijie Wu, Minjia Zheng","doi":"10.1049/cvi2.70030","DOIUrl":"https://doi.org/10.1049/cvi2.70030","url":null,"abstract":"In the current context of the extensive use of deep neural networks, it has been observed that neural network models are vulnerable to adversarial perturbations, which may lead to unexpected results. In this paper, we introduce an Adversarial Purification Model rooted in latent representation compression, aimed at enhancing the robustness of deep learning models. Initially, we employ an encoder-decoder architecture inspired by the U-net to extract features from input samples. Subsequently, these features undergo a process of information compression to remove adversarial perturbations from the latent space. To counteract the model's tendency to overly focus on fine-grained details of input samples, resulting in ineffective adversarial sample purification, an early freezing mechanism is introduced during the encoder training process. We tested our model's ability to purify adversarial samples generated from the CIFAR-10, CIFAR-100, and ImageNet datasets using various methods. These samples were then used to test ResNet, an image recognition classifiers. Our experiments covered different resolutions and attack types to fully assess LRCM's effectiveness against adversarial attacks. We also compared LRCM with other defence strategies, demonstrating its strong defensive capabilities.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144085290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Geometric Edge Modelling in Self-Supervised Learning for Enhanced Indoor Depth Estimation 基于自监督学习的几何边缘建模增强室内深度估计

IF 1.5 4区计算机科学

IET Computer Vision Pub Date : 2025-05-12 DOI: 10.1049/cvi2.70026

Niclas Joswig, Laura Ruotsalainen

{"title":"Geometric Edge Modelling in Self-Supervised Learning for Enhanced Indoor Depth Estimation","authors":"Niclas Joswig, Laura Ruotsalainen","doi":"10.1049/cvi2.70026","DOIUrl":"https://doi.org/10.1049/cvi2.70026","url":null,"abstract":"Recently, the accuracy of self-supervised deep learning models for indoor depth estimation has approached that of supervised models by improving the supervision in planar regions. However, a common issue with integrating multiple planar priors is the generation of oversmooth depth maps, leading to unrealistic and erroneous depth representations at edges. Despite the fact that edge pixels only cover a small part of the image, they are of high significance for downstream tasks such as visual odometry, where image features, essential for motion computation, are mostly located at edges. To improve erroneous depth predictions at edge regions, we delve into the self-supervised training process, identifying its limitations and using these insights to develop a geometric edge model. Building on this, we introduce a novel algorithm that utilises the smooth depth predictions of existing models and colour image data to accurately identify edge pixels. After finding the edge pixels, our approach generates targeted self-supervision in these zones by interpolating depth values from adjacent planar areas towards the edges. We integrate the proposed algorithms into a novel loss function that encourages neural networks to predict sharper and more accurate depth edges in indoor scenes. To validate our methodology, we incorporated the proposed edge-enhancing loss function into a state-of-the-art self-supervised depth estimation framework. Our results demonstrate a notable improvement in the accuracy of edge depth predictions and a 19% improvement in visual odometry when using our depth model to generate RGB-D input, compared to the baseline model.","PeriodicalId":56304,"journal":{"name":"IET Computer Vision","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cvi2.70026","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143938938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0