Recently, transformer-based backbones show superior performance over the convolutional counterparts in computer vision. Due to quadratic complexity with respect to the token number in global attention, local attention is always adopted in low-level image processing with linear complexity. However, the limited receptive field is harmful to the performance. In this paper, motivated by Octave convolution, we propose a transformer-based single image super-resolution (SISR) model, which explicitly embeds dynamic frequency decomposition into the standard local transformer. All the frequency components are continuously updated and re-assigned via intra-scale attention and inter-scale interaction, respectively. Specifically, the attention in low resolution is enough for low-frequency features, which not only increases the receptive field, but also decreases the complexity. Compared with the standard local transformer, the proposed FDRTran layer simultaneously decreases FLOPs and parameters. By contrast, Octave convolution only decreases FLOPs of the standard convolution, but keeps the parameter number unchanged. In addition, the restart mechanism is proposed for every a few frequency updates, which first fuses the low and high frequency, then decomposes the features again. In this way, the features can be decomposed in multiple viewpoints by learnable parameters, which avoids the risk of early saturation for frequency representation. Furthermore, based on the FDRTran layer with restart mechanism, the proposed FDRNet is the first transformer backbone for SISR which discusses the Octave design. Sufficient experiments show our model reaches state-of-the-art performance on 6 synthetic and real datasets. The code and the models are available at https://github.com/catnip1029/FDRNet .
{"title":"Image Super-Resolution via Efficient Transformer Embedding Frequency Decomposition With Restart","authors":"Yifan Zuo;Wenhao Yao;Yuqi Hu;Yuming Fang;Wei Liu;Yuxin Peng","doi":"10.1109/TIP.2024.3444317","DOIUrl":"10.1109/TIP.2024.3444317","url":null,"abstract":"Recently, transformer-based backbones show superior performance over the convolutional counterparts in computer vision. Due to quadratic complexity with respect to the token number in global attention, local attention is always adopted in low-level image processing with linear complexity. However, the limited receptive field is harmful to the performance. In this paper, motivated by Octave convolution, we propose a transformer-based single image super-resolution (SISR) model, which explicitly embeds dynamic frequency decomposition into the standard local transformer. All the frequency components are continuously updated and re-assigned via intra-scale attention and inter-scale interaction, respectively. Specifically, the attention in low resolution is enough for low-frequency features, which not only increases the receptive field, but also decreases the complexity. Compared with the standard local transformer, the proposed FDRTran layer simultaneously decreases FLOPs and parameters. By contrast, Octave convolution only decreases FLOPs of the standard convolution, but keeps the parameter number unchanged. In addition, the restart mechanism is proposed for every a few frequency updates, which first fuses the low and high frequency, then decomposes the features again. In this way, the features can be decomposed in multiple viewpoints by learnable parameters, which avoids the risk of early saturation for frequency representation. Furthermore, based on the FDRTran layer with restart mechanism, the proposed FDRNet is the first transformer backbone for SISR which discusses the Octave design. Sufficient experiments show our model reaches state-of-the-art performance on 6 synthetic and real datasets. The code and the models are available at \u0000<uri>https://github.com/catnip1029/FDRNet</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142019915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/TIP.2024.3431915
Wang Luo, Huan Ren, Tianzhu Zhangd, Wenfei Yang, Yongdong Zhang
Weakly-supervised Temporal Action Localization (WTAL) aims to localize action instances with only video-level labels during training, where two primary issues are localization incompleteness and background interference. To relieve these two issues, recent methods adopt an attention mechanism to activate action instances and simultaneously suppress background ones, which have achieved remarkable progress. Nevertheless, we argue that these two issues have not been well resolved yet. On the one hand, the attention mechanism adopts fixed weights for different videos, which are incapable of handling the diversity of different videos, thus deficient in addressing the problem of localization incompleteness. On the other hand, previous methods only focus on learning the foreground attention and the attention weights usually suffer from ambiguity, resulting in difficulty of suppressing background interference. To deal with the above issues, in this paper we propose an Adaptive Prototype Learning (APL) method for WTAL, which includes two key designs: (1) an Adaptive Transformer Network (ATN) to explicitly model background and learn video-adaptive prototypes for each specific video, (2) an OT-based Collaborative (OTC) training strategy to guide the learning of prototypes and remove the ambiguity of the foreground-background separation by introducing an Optimal Transport (OT) algorithm into the collaborative training scheme between RGB and FLOW streams. These two key designs can work together to learn video-adaptive prototypes and solve the above two issues, achieving robust localization. Extensive experimental results on two standard benchmarks (THUMOS14 and ActivityNet) demonstrate that our proposed APL performs favorably against state-of-the-art methods.
{"title":"Adaptive Prototype Learning for Weakly-supervised Temporal Action Localization.","authors":"Wang Luo, Huan Ren, Tianzhu Zhangd, Wenfei Yang, Yongdong Zhang","doi":"10.1109/TIP.2024.3431915","DOIUrl":"10.1109/TIP.2024.3431915","url":null,"abstract":"<p><p>Weakly-supervised Temporal Action Localization (WTAL) aims to localize action instances with only video-level labels during training, where two primary issues are localization incompleteness and background interference. To relieve these two issues, recent methods adopt an attention mechanism to activate action instances and simultaneously suppress background ones, which have achieved remarkable progress. Nevertheless, we argue that these two issues have not been well resolved yet. On the one hand, the attention mechanism adopts fixed weights for different videos, which are incapable of handling the diversity of different videos, thus deficient in addressing the problem of localization incompleteness. On the other hand, previous methods only focus on learning the foreground attention and the attention weights usually suffer from ambiguity, resulting in difficulty of suppressing background interference. To deal with the above issues, in this paper we propose an Adaptive Prototype Learning (APL) method for WTAL, which includes two key designs: (1) an Adaptive Transformer Network (ATN) to explicitly model background and learn video-adaptive prototypes for each specific video, (2) an OT-based Collaborative (OTC) training strategy to guide the learning of prototypes and remove the ambiguity of the foreground-background separation by introducing an Optimal Transport (OT) algorithm into the collaborative training scheme between RGB and FLOW streams. These two key designs can work together to learn video-adaptive prototypes and solve the above two issues, achieving robust localization. Extensive experimental results on two standard benchmarks (THUMOS14 and ActivityNet) demonstrate that our proposed APL performs favorably against state-of-the-art methods.</p>","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142010110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/TIP.2024.3437234
Yazhou Liu;Zhiyong Liu
This work presents a new completion method that specifically designed for low-overlapping partial point cloud registration. Based on the assumption that the candidate partial point clouds to be registered belong to the same target, the proposed mutual prior based completion (MPC) method uses these candidate partial point clouds as completion reference for each other to extend their overlapping regions. Without relying on shape prior knowledge, MPC can work for different types of point clouds, such as object, room scene, and street view. The main challenge of this mutual reference approach is that partial clouds without spatial alignment cannot provide a reliable completion reference. Based on the mutual information maximization, a progressive completion structure is developed to achieve pose, feature representation and completion alignment between input point clouds. Experiments on public datasets show encouraging results. Especially for the low-overlapping cases, compared with the state-of-the-art (SOTA) models, the size of overlapping regions can be increased by about 15.0%, and the rotation and translation error can be reduced by 30.8% and 57.7% respectively.
{"title":"Low Overlapping Point Cloud Registration Using Mutual Prior Based Completion Network","authors":"Yazhou Liu;Zhiyong Liu","doi":"10.1109/TIP.2024.3437234","DOIUrl":"10.1109/TIP.2024.3437234","url":null,"abstract":"This work presents a new completion method that specifically designed for low-overlapping partial point cloud registration. Based on the assumption that the candidate partial point clouds to be registered belong to the same target, the proposed mutual prior based completion (MPC) method uses these candidate partial point clouds as completion reference for each other to extend their overlapping regions. Without relying on shape prior knowledge, MPC can work for different types of point clouds, such as object, room scene, and street view. The main challenge of this mutual reference approach is that partial clouds without spatial alignment cannot provide a reliable completion reference. Based on the mutual information maximization, a progressive completion structure is developed to achieve pose, feature representation and completion alignment between input point clouds. Experiments on public datasets show encouraging results. Especially for the low-overlapping cases, compared with the state-of-the-art (SOTA) models, the size of overlapping regions can be increased by about 15.0%, and the rotation and translation error can be reduced by 30.8% and 57.7% respectively.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142010111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-19DOI: 10.1109/TIP.2024.3436651
Sébastien Herbreteau;Charles Kervrann
In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image (a.k.a., self-supervised or zero-shot) methods perform denoising solely based on the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network-based techniques, while being much faster and fully interpretable.
{"title":"Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising","authors":"Sébastien Herbreteau;Charles Kervrann","doi":"10.1109/TIP.2024.3436651","DOIUrl":"10.1109/TIP.2024.3436651","url":null,"abstract":"In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image (a.k.a., self-supervised or zero-shot) methods perform denoising solely based on the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network-based techniques, while being much faster and fully interpretable.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142006158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-19DOI: 10.1109/TIP.2024.3442614
Yan Li;Xia Cai;Chunwei Wu;Xiao Lin;Guitao Cao
Despite the large-scale adoption of Artificial Intelligence (AI) models in healthcare, there is an urgent need for trustworthy tools to rigorously backtrack the model decisions so that they behave reliably. Counterfactual explanations take a counter-intuitive approach to allow users to explore “what if” scenarios gradually becoming popular in the trustworthy field. However, most previous work on model’s counterfactual explanation cannot generate in-distribution attribution credibly, produces adversarial examples, or fails to give a confidence interval for the explanation. Hence, in this paper, we propose a novel approach that generates counterfactuals in locally smooth directed semantic embedding space, and at the same time gives an uncertainty estimate in the counterfactual generation process. Specifically, we identify low-dimensional directed semantic embedding space based on Principal Component Analysis (PCA) applied in differential generative model. Then, we propose latent space smoothing regularization to rectify counterfactual search within in-distribution, such that visually-imperceptible changes are more robust to adversarial perturbations. Moreover, we put forth an uncertainty estimation framework for evaluating counterfactual uncertainty. Extensive experiments on several challenging realistic Chest X-ray and CelebA datasets show that our approach performs consistently well and better than the existing several state-of-the-art baseline approaches.
尽管人工智能（AI）模型在医疗保健领域得到了大规模应用，但仍迫切需要可信的工具来严格回溯模型的决策，使其行为可靠。反事实解释采用反直觉的方法，允许用户探索 "如果 "场景，逐渐在可信领域流行起来。然而，以往大多数关于模型反事实解释的工作都无法可信地生成分布内归因，产生对抗性示例，或无法给出解释的置信区间。因此，在本文中，我们提出了一种在局部平滑的有向语义嵌入空间中生成反事实的新方法，同时给出了反事实生成过程中的不确定性估计。具体来说，我们根据应用于差分生成模型的主成分分析法（PCA）确定低维有向语义嵌入空间。然后，我们提出了潜在空间平滑正则化方法，以纠正分布内的反事实搜索，从而使视觉上可感知的变化对对抗性扰动更加稳健。此外，我们还提出了一个用于评估反事实不确定性的不确定性估计框架。在几个具有挑战性的现实胸部 X 射线和 CelebA 数据集上进行的广泛实验表明，我们的方法始终表现良好，优于现有的几种最先进的基线方法。
{"title":"A Trustworthy Counterfactual Explanation Method With Latent Space Smoothing","authors":"Yan Li;Xia Cai;Chunwei Wu;Xiao Lin;Guitao Cao","doi":"10.1109/TIP.2024.3442614","DOIUrl":"10.1109/TIP.2024.3442614","url":null,"abstract":"Despite the large-scale adoption of Artificial Intelligence (AI) models in healthcare, there is an urgent need for trustworthy tools to rigorously backtrack the model decisions so that they behave reliably. Counterfactual explanations take a counter-intuitive approach to allow users to explore “what if” scenarios gradually becoming popular in the trustworthy field. However, most previous work on model’s counterfactual explanation cannot generate in-distribution attribution credibly, produces adversarial examples, or fails to give a confidence interval for the explanation. Hence, in this paper, we propose a novel approach that generates counterfactuals in locally smooth directed semantic embedding space, and at the same time gives an uncertainty estimate in the counterfactual generation process. Specifically, we identify low-dimensional directed semantic embedding space based on Principal Component Analysis (PCA) applied in differential generative model. Then, we propose latent space smoothing regularization to rectify counterfactual search within in-distribution, such that visually-imperceptible changes are more robust to adversarial perturbations. Moreover, we put forth an uncertainty estimation framework for evaluating counterfactual uncertainty. Extensive experiments on several challenging realistic Chest X-ray and CelebA datasets show that our approach performs consistently well and better than the existing several state-of-the-art baseline approaches.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142006155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-19DOI: 10.1109/TIP.2024.3442610
Jian-Xun Mi;Junchang He;Weisheng Li
In scenarios where identifying face information in the visible spectrum (VIS) is challenging due to poor lighting conditions, the use of near-infrared (NIR) and thermal (TH) cameras can provide viable alternatives. However, the unique data distribution of images captured by these cameras compared to VIS images presents challenges in matching face identities. To address these challenges, we propose a novel image transformation framework. The framework includes feature extraction from the input image, followed by a transformation network that generates target domain images with perceptual fidelity. Additionally, a reconstruction network preserves original information by reconstructing the original domain image from the extracted features. By considering the correlation between features from both domains, our framework utilizes paired data obtained from the same individual. We apply this framework to two well-established image-to-image transformation models, pix2pix and CycleGAN, known as CRC-pix2pix and CRC-CycleGAN respectively. The versatility of our approach allows extension to other models based on pix2pix or CycleGAN architectures. Our models generate high-quality images while preserving the identity information of the original face. Performance evaluation on TFW and BUAA NIR-VIS datasets demonstrates the superiority of our models in terms of generated image face matching and evaluation metrics such as SSIM, MSE, PSNR, and LPIPS. Moreover, we introduce the CQUPT-VIS-TH dataset, which enriches the paired dataset with thermal-visual face data capturing various angles and expressions.
{"title":"Deep Cross-View Reconstruction GAN Based on Correlated Subspace for Multi-View Transformation","authors":"Jian-Xun Mi;Junchang He;Weisheng Li","doi":"10.1109/TIP.2024.3442610","DOIUrl":"10.1109/TIP.2024.3442610","url":null,"abstract":"In scenarios where identifying face information in the visible spectrum (VIS) is challenging due to poor lighting conditions, the use of near-infrared (NIR) and thermal (TH) cameras can provide viable alternatives. However, the unique data distribution of images captured by these cameras compared to VIS images presents challenges in matching face identities. To address these challenges, we propose a novel image transformation framework. The framework includes feature extraction from the input image, followed by a transformation network that generates target domain images with perceptual fidelity. Additionally, a reconstruction network preserves original information by reconstructing the original domain image from the extracted features. By considering the correlation between features from both domains, our framework utilizes paired data obtained from the same individual. We apply this framework to two well-established image-to-image transformation models, pix2pix and CycleGAN, known as CRC-pix2pix and CRC-CycleGAN respectively. The versatility of our approach allows extension to other models based on pix2pix or CycleGAN architectures. Our models generate high-quality images while preserving the identity information of the original face. Performance evaluation on TFW and BUAA NIR-VIS datasets demonstrates the superiority of our models in terms of generated image face matching and evaluation metrics such as SSIM, MSE, PSNR, and LPIPS. Moreover, we introduce the CQUPT-VIS-TH dataset, which enriches the paired dataset with thermal-visual face data capturing various angles and expressions.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142006156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Blind image super-resolution (SR) aims to recover a high-resolution (HR) image from its low-resolution (LR) counterpart under the assumption of unknown degradations. Many existing blind SR methods rely on supervising ground-truth kernels referred to as explicit degradation estimators. However, it is very challenging to obtain the ground-truths for different degradations kernels. Moreover, most of these methods rely on heavy backbone networks, which demand extensive computational resources. Implicit degradation estimators do not require the availability of ground truth kernels, but they see a significant performance gap with the explicit degradation estimators due to such missing information. We present a novel approach that significantly narrows such a gap by means of a lightweight architecture that implicitly learns the degradation kernel with the help of a novel loss component. The kernel is exploited by a learnable Wiener filter that performs efficient deconvolution in the Fourier domain by deriving a closed-form solution. Inspired by prompt-based learning, we also propose a novel degradation-conditioned prompt layer that exploits the estimated kernel to drive the focus on the discriminative contextual information that guides the reconstruction process in recovering the latent HR image. Extensive experiments under different degradation settings demonstrate that our model, named PL-IDENet, yields PSNR and SSIM improvements of more than $0.4dB$ and 1.3%, and $1.4dB$ and 4.8% to the best implicit and explicit blind-SR method, respectively. These results are achieved while maintaining a substantially lower number of parameters/FLOPs (i.e., 25% and 68% fewer parameters than best implicit and explicit methods, respectively).
{"title":"Lightweight Prompt Learning Implicit Degradation Estimation Network for Blind Super Resolution","authors":"Asif Hussain Khan;Christian Micheloni;Niki Martinel","doi":"10.1109/TIP.2024.3442613","DOIUrl":"10.1109/TIP.2024.3442613","url":null,"abstract":"Blind image super-resolution (SR) aims to recover a high-resolution (HR) image from its low-resolution (LR) counterpart under the assumption of unknown degradations. Many existing blind SR methods rely on supervising ground-truth kernels referred to as explicit degradation estimators. However, it is very challenging to obtain the ground-truths for different degradations kernels. Moreover, most of these methods rely on heavy backbone networks, which demand extensive computational resources. Implicit degradation estimators do not require the availability of ground truth kernels, but they see a significant performance gap with the explicit degradation estimators due to such missing information. We present a novel approach that significantly narrows such a gap by means of a lightweight architecture that implicitly learns the degradation kernel with the help of a novel loss component. The kernel is exploited by a learnable Wiener filter that performs efficient deconvolution in the Fourier domain by deriving a closed-form solution. Inspired by prompt-based learning, we also propose a novel degradation-conditioned prompt layer that exploits the estimated kernel to drive the focus on the discriminative contextual information that guides the reconstruction process in recovering the latent HR image. Extensive experiments under different degradation settings demonstrate that our model, named PL-IDENet, yields PSNR and SSIM improvements of more than \u0000<inline-formula> <tex-math>$0.4dB$ </tex-math></inline-formula>\u0000 and 1.3%, and \u0000<inline-formula> <tex-math>$1.4dB$ </tex-math></inline-formula>\u0000 and 4.8% to the best implicit and explicit blind-SR method, respectively. These results are achieved while maintaining a substantially lower number of parameters/FLOPs (i.e., 25% and 68% fewer parameters than best implicit and explicit methods, respectively).","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142006157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-16DOI: 10.1109/TIP.2024.3441370
Qi Jiang;Shaohua Gao;Yao Gao;Kailun Yang;Zhonghua Yi;Hao Shi;Lei Sun;Kaiwei Wang
High-quality panoramic images with a Field of View (FoV) of 360° are essential for contemporary panoramic computer vision tasks. However, conventional imaging systems come with sophisticated lens designs and heavy optical components. This disqualifies their usage in many mobile and wearable applications where thin and portable, minimalist imaging systems are desired. In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging. With less than three spherical lenses, a Minimalist Panoramic Imaging Prototype (MPIP) is constructed based on the design of the Panoramic Annular Lens (PAL), but with low-quality imaging results due to aberrations and small image plane size. We propose two pipelines, i.e. Aberration Correction (AC) and Super-Resolution and Aberration Correction (SR&AC), to solve the image quality problems of MPIP, with imaging sensors of small and large pixel size, respectively. To leverage the prior information of the optical system, we propose a Point Spread Function (PSF) representation method to produce a PSF map as an additional modality. A PSF-aware Aberration-image Recovery Transformer (PART) is designed as a universal network for the two pipelines, in which the self-attention calculation and feature extraction are guided by the PSF map. We train PART on synthetic image pairs from simulation and put forward the PALHQ dataset to fill the gap of real-world high-quality PAL images for low-level vision. A comprehensive variety of experiments on synthetic and real-world benchmarks demonstrates the impressive imaging results of PCIE and the effectiveness of the PSF representation. We further deliver heuristic experimental findings for minimalist and high-quality panoramic imaging, in terms of the choices of prototype and pipeline, network architecture, training strategies, and dataset construction. Our dataset and code will be available at https://github.com/zju-jiangqi/PCIE-PART .
{"title":"Minimalist and High-Quality Panoramic Imaging With PSF-Aware Transformers","authors":"Qi Jiang;Shaohua Gao;Yao Gao;Kailun Yang;Zhonghua Yi;Hao Shi;Lei Sun;Kaiwei Wang","doi":"10.1109/TIP.2024.3441370","DOIUrl":"10.1109/TIP.2024.3441370","url":null,"abstract":"High-quality panoramic images with a Field of View (FoV) of 360° are essential for contemporary panoramic computer vision tasks. However, conventional imaging systems come with sophisticated lens designs and heavy optical components. This disqualifies their usage in many mobile and wearable applications where thin and portable, minimalist imaging systems are desired. In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging. With less than three spherical lenses, a Minimalist Panoramic Imaging Prototype (MPIP) is constructed based on the design of the Panoramic Annular Lens (PAL), but with low-quality imaging results due to aberrations and small image plane size. We propose two pipelines, i.e. Aberration Correction (AC) and Super-Resolution and Aberration Correction (SR&AC), to solve the image quality problems of MPIP, with imaging sensors of small and large pixel size, respectively. To leverage the prior information of the optical system, we propose a Point Spread Function (PSF) representation method to produce a PSF map as an additional modality. A PSF-aware Aberration-image Recovery Transformer (PART) is designed as a universal network for the two pipelines, in which the self-attention calculation and feature extraction are guided by the PSF map. We train PART on synthetic image pairs from simulation and put forward the PALHQ dataset to fill the gap of real-world high-quality PAL images for low-level vision. A comprehensive variety of experiments on synthetic and real-world benchmarks demonstrates the impressive imaging results of PCIE and the effectiveness of the PSF representation. We further deliver heuristic experimental findings for minimalist and high-quality panoramic imaging, in terms of the choices of prototype and pipeline, network architecture, training strategies, and dataset construction. Our dataset and code will be available at \u0000<uri>https://github.com/zju-jiangqi/PCIE-PART</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141992546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-16DOI: 10.1109/TIP.2024.3441813
Jiahui Wang;Qin Xu;Bo Jiang;Bin Luo;Jinhui Tang
Fine-grained visual classification aims to classify similar sub-categories with the challenges of large variations within the same sub-category and high visual similarities between different sub-categories. Recently, methods that extract semantic parts of the discriminative regions have attracted increasing attention. However, most existing methods extract the part features via rectangular bounding boxes by object detection module or attention mechanism, which makes it difficult to capture the rich shape information of objects. In this paper, we propose a novel Multi-Granularity Part Sampling Attention (MPSA) network for fine-grained visual classification. First, a novel multi-granularity part retrospect block is designed to extract the part information of different scales and enhance the high-level feature representation with discriminative part features of different granularities. Then, to extract part features of various shapes at each granularity, we propose part sampling attention, which can sample the implicit semantic parts on the feature maps comprehensively. The proposed part sampling attention not only considers the importance of sampled parts but also adopts the part dropout to reduce the overfitting issue. In addition, we propose a novel multi-granularity fusion method to highlight the foreground features and suppress the background noises with the assistance of the gradient class activation map. Experimental results demonstrate that the proposed MPSA achieves state-of-the-art performance on four commonly used fine-grained visual classification benchmarks. The source code is publicly available at https://github.com/mobulan/MPSA .
{"title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","authors":"Jiahui Wang;Qin Xu;Bo Jiang;Bin Luo;Jinhui Tang","doi":"10.1109/TIP.2024.3441813","DOIUrl":"10.1109/TIP.2024.3441813","url":null,"abstract":"Fine-grained visual classification aims to classify similar sub-categories with the challenges of large variations within the same sub-category and high visual similarities between different sub-categories. Recently, methods that extract semantic parts of the discriminative regions have attracted increasing attention. However, most existing methods extract the part features via rectangular bounding boxes by object detection module or attention mechanism, which makes it difficult to capture the rich shape information of objects. In this paper, we propose a novel Multi-Granularity Part Sampling Attention (MPSA) network for fine-grained visual classification. First, a novel multi-granularity part retrospect block is designed to extract the part information of different scales and enhance the high-level feature representation with discriminative part features of different granularities. Then, to extract part features of various shapes at each granularity, we propose part sampling attention, which can sample the implicit semantic parts on the feature maps comprehensively. The proposed part sampling attention not only considers the importance of sampled parts but also adopts the part dropout to reduce the overfitting issue. In addition, we propose a novel multi-granularity fusion method to highlight the foreground features and suppress the background noises with the assistance of the gradient class activation map. Experimental results demonstrate that the proposed MPSA achieves state-of-the-art performance on four commonly used fine-grained visual classification benchmarks. The source code is publicly available at \u0000<uri>https://github.com/mobulan/MPSA</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141992474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-16DOI: 10.1109/TIP.2024.3441930
Shansi Zhang;Yaping Zhao;Edmund Y. Lam
Light field (LF) images enable numerous applications due to their ability to capture information for multiple views. Semantic segmentation is an essential task for LF scene understanding. However, existing supervised methods heavily rely on a large number of pixel-wise annotations. To relieve this problem, we propose a semi-supervised LF semantic segmentation method that requires only a small subset of labeled data and harnesses the LF disparity information. First, we design an unsupervised disparity estimation network, which can determine the disparity map for every view. With the estimated disparity maps, we generate pseudo-labels along with their weight maps for the peripheral views when only the labels of central views are available. We then merge the predictions from multiple views to obtain more reliable pseudo-labels for unlabeled data, and introduce a disparity-semantics consistency loss to enforce structure similarity. Moreover, we develop a comprehensive contrastive learning scheme that includes a pixel-level strategy to enhance feature representations and an object-level strategy to improve segmentation for individual objects. Our method demonstrates state-of-the-art performance on the benchmark LF semantic segmentation dataset under a variety of training settings and achieves comparable performance to supervised methods when trained under 1/2 protocol.
{"title":"Semi-Supervised Semantic Segmentation for Light Field Images Using Disparity Information","authors":"Shansi Zhang;Yaping Zhao;Edmund Y. Lam","doi":"10.1109/TIP.2024.3441930","DOIUrl":"10.1109/TIP.2024.3441930","url":null,"abstract":"Light field (LF) images enable numerous applications due to their ability to capture information for multiple views. Semantic segmentation is an essential task for LF scene understanding. However, existing supervised methods heavily rely on a large number of pixel-wise annotations. To relieve this problem, we propose a semi-supervised LF semantic segmentation method that requires only a small subset of labeled data and harnesses the LF disparity information. First, we design an unsupervised disparity estimation network, which can determine the disparity map for every view. With the estimated disparity maps, we generate pseudo-labels along with their weight maps for the peripheral views when only the labels of central views are available. We then merge the predictions from multiple views to obtain more reliable pseudo-labels for unlabeled data, and introduce a disparity-semantics consistency loss to enforce structure similarity. Moreover, we develop a comprehensive contrastive learning scheme that includes a pixel-level strategy to enhance feature representations and an object-level strategy to improve segmentation for individual objects. Our method demonstrates state-of-the-art performance on the benchmark LF semantic segmentation dataset under a variety of training settings and achieves comparable performance to supervised methods when trained under 1/2 protocol.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141992475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：