With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, all existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. During recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. Experimental results show that our proposed MISC is suitable for compressing both traditional Natural Sense Images (NSIs) and emerging AI-Generated Images (AIGIs) content. It can achieve optimal consistency and perception results while saving 50% bitrate, which has strong potential applications in the next generation of storage and communication. The code will be released on https://github.com/lcysyzxdxc/MISC.
{"title":"MISC: Ultra-Low Bitrate Image Semantic Compression Driven by Large Multimodal Model","authors":"Chunyi Li;Guo Lu;Donghui Feng;Haoning Wu;Zicheng Zhang;Xiaohong Liu;Guangtao Zhai;Weisi Lin;Wenjun Zhang","doi":"10.1109/TIP.2024.3515874","DOIUrl":"10.1109/TIP.2024.3515874","url":null,"abstract":"With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, all existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. During recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. Experimental results show that our proposed MISC is suitable for compressing both traditional Natural Sense Images (NSIs) and emerging AI-Generated Images (AIGIs) content. It can achieve optimal consistency and perception results while saving 50% bitrate, which has strong potential applications in the next generation of storage and communication. The code will be released on <uri>https://github.com/lcysyzxdxc/MISC</uri>.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"335-349"},"PeriodicalIF":0.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888341","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}
Self-supervised point cloud representation learning aims to acquire robust and general feature representations from unlabeled data. Recently, masked point modeling-based methods have shown significant performance improvements for point cloud understanding, yet these methods rely on overlapping grouping strategies (k-nearest neighbor algorithm) resulting in early leakage of structural information of mask groups, and overlook the semantic modeling of object components resulting in parts with the same semantics having obvious feature differences due to position differences. In this work, we rethink grouping strategies and pretext tasks that are more suitable for self-supervised point cloud representation learning and propose a novel hierarchical masked representation learning method, including an optimal transport-based hierarchical grouping strategy, a prototype-based part modeling module, and a hierarchical attention encoder. The proposed method enjoys several merits. First, the proposed grouping strategy partitions the point cloud into non-overlapping groups, eliminating the early leakage of structural information in the masked groups. Second, the proposed prototype-based part modeling module dynamically models different object components, ensuring feature consistency on parts with the same semantics. Extensive experiments on four downstream tasks demonstrate that our method surpasses state-of-the-art 3D representation learning methods. Furthermore, Comprehensive ablation studies and visualizations demonstrate the effectiveness of the proposed modules.
{"title":"Rethinking Masked Representation Learning for 3D Point Cloud Understanding","authors":"Chuxin Wang;Yixin Zha;Jianfeng He;Wenfei Yang;Tianzhu Zhang","doi":"10.1109/TIP.2024.3520008","DOIUrl":"10.1109/TIP.2024.3520008","url":null,"abstract":"Self-supervised point cloud representation learning aims to acquire robust and general feature representations from unlabeled data. Recently, masked point modeling-based methods have shown significant performance improvements for point cloud understanding, yet these methods rely on overlapping grouping strategies (k-nearest neighbor algorithm) resulting in early leakage of structural information of mask groups, and overlook the semantic modeling of object components resulting in parts with the same semantics having obvious feature differences due to position differences. In this work, we rethink grouping strategies and pretext tasks that are more suitable for self-supervised point cloud representation learning and propose a novel hierarchical masked representation learning method, including an optimal transport-based hierarchical grouping strategy, a prototype-based part modeling module, and a hierarchical attention encoder. The proposed method enjoys several merits. First, the proposed grouping strategy partitions the point cloud into non-overlapping groups, eliminating the early leakage of structural information in the masked groups. Second, the proposed prototype-based part modeling module dynamically models different object components, ensuring feature consistency on parts with the same semantics. Extensive experiments on four downstream tasks demonstrate that our method surpasses state-of-the-art 3D representation learning methods. Furthermore, Comprehensive ablation studies and visualizations demonstrate the effectiveness of the proposed modules.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"247-262"},"PeriodicalIF":0.0,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888343","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 : 2024-12-25DOI: 10.1109/TIP.2024.3512354
Shuai Zhao;Ruijie Quan;Linchao Zhu;Yi Yang
Pre-trained vision-language models (VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre-trained on a single modality, namely, the visual modality, despite the potential of VLMs to serve as powerful scene text readers. For example, CLIP can robustly identify regular (horizontal) and irregular (rotated, curved, blurred, or occluded) text in images. With such merits, we transform CLIP into a scene text reader and introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP. It has two encoder-decoder branches: a visual branch and a cross-modal branch. The visual branch provides an initial prediction based on the visual feature, and the cross-modal branch refines this prediction by addressing the discrepancy between the visual feature and text semantics. To fully leverage the capabilities of both branches, we design a dual predict-and-refine decoding scheme for inference. We scale CLIP4STR in terms of the model size, pre-training data, and training data, achieving state-of-the-art performance on 13 STR benchmarks. Additionally, a comprehensive empirical study is provided to enhance the understanding of the adaptation of CLIP to STR. Our method establishes a simple yet strong baseline for future STR research with VLMs.
{"title":"CLIP4STR: A Simple Baseline for Scene Text Recognition With Pre-Trained Vision-Language Model","authors":"Shuai Zhao;Ruijie Quan;Linchao Zhu;Yi Yang","doi":"10.1109/TIP.2024.3512354","DOIUrl":"10.1109/TIP.2024.3512354","url":null,"abstract":"Pre-trained vision-language models (VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre-trained on a single modality, namely, the visual modality, despite the potential of VLMs to serve as powerful scene text readers. For example, CLIP can robustly identify regular (horizontal) and irregular (rotated, curved, blurred, or occluded) text in images. With such merits, we transform CLIP into a scene text reader and introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP. It has two encoder-decoder branches: a visual branch and a cross-modal branch. The visual branch provides an initial prediction based on the visual feature, and the cross-modal branch refines this prediction by addressing the discrepancy between the visual feature and text semantics. To fully leverage the capabilities of both branches, we design a dual predict-and-refine decoding scheme for inference. We scale CLIP4STR in terms of the model size, pre-training data, and training data, achieving state-of-the-art performance on 13 STR benchmarks. Additionally, a comprehensive empirical study is provided to enhance the understanding of the adaptation of CLIP to STR. Our method establishes a simple yet strong baseline for future STR research with VLMs.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6893-6904"},"PeriodicalIF":0.0,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888344","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 : 2024-12-25DOI: 10.1109/TIP.2024.3520423
Haochen Yu;Weixi Gong;Jiansheng Chen;Huimin Ma
Controllable 3D-aware scene synthesis seeks to disentangle the various latent codes in the implicit space enabling the generation network to create highly realistic images with 3D consistency. Recent approaches often integrate Neural Radiance Fields with the upsampling method of StyleGAN2, employing Convolutions with style modulation to transform spatial coordinates into frequency domain representations. Our analysis indicates that this approach can give rise to a bubble phenomenon in StyleNeRF. We argue that the style modulation introduces extraneous information into the implicit space, disrupting 3D implicit modeling and degrading image quality. We introduce HomuGAN, incorporating two key improvements. First, we disentangle the style modulation applied to implicit modeling from that utilized for super-resolution, thus alleviating the bubble phenomenon. Second, we introduce Cylindrical Spatial-Constrained Sampling and Parabolic Sampling. The latter sampling method, as an alternative method to the former, specifically contributes to the performance of foreground modeling of vehicles. We evaluate HomuGAN on publicly available datasets, comparing its performance to existing methods. Empirical results demonstrate that our model achieves the best performance, exhibiting relatively outstanding disentanglement capability. Moreover, HomuGAN addresses the training instability problem observed in StyleNeRF and reduces the bubble phenomenon.
{"title":"HomuGAN: A 3D-Aware GAN With the Method of Cylindrical Spatial-Constrained Sampling","authors":"Haochen Yu;Weixi Gong;Jiansheng Chen;Huimin Ma","doi":"10.1109/TIP.2024.3520423","DOIUrl":"10.1109/TIP.2024.3520423","url":null,"abstract":"Controllable 3D-aware scene synthesis seeks to disentangle the various latent codes in the implicit space enabling the generation network to create highly realistic images with 3D consistency. Recent approaches often integrate Neural Radiance Fields with the upsampling method of StyleGAN2, employing Convolutions with style modulation to transform spatial coordinates into frequency domain representations. Our analysis indicates that this approach can give rise to a bubble phenomenon in StyleNeRF. We argue that the style modulation introduces extraneous information into the implicit space, disrupting 3D implicit modeling and degrading image quality. We introduce HomuGAN, incorporating two key improvements. First, we disentangle the style modulation applied to implicit modeling from that utilized for super-resolution, thus alleviating the bubble phenomenon. Second, we introduce Cylindrical Spatial-Constrained Sampling and Parabolic Sampling. The latter sampling method, as an alternative method to the former, specifically contributes to the performance of foreground modeling of vehicles. We evaluate HomuGAN on publicly available datasets, comparing its performance to existing methods. Empirical results demonstrate that our model achieves the best performance, exhibiting relatively outstanding disentanglement capability. Moreover, HomuGAN addresses the training instability problem observed in StyleNeRF and reduces the bubble phenomenon.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"320-334"},"PeriodicalIF":0.0,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888342","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 : 2024-12-25DOI: 10.1109/TIP.2024.3515872
Wenhao Li;Mengyuan Liu;Hong Liu;Bin Ren;Xia Li;Yingxuan You;Nicu Sebe
Regression-based 3D human pose and shape estimation often fall into one of two different paradigms. Parametric approaches, which regress the parameters of a human body model, tend to produce physically plausible but image-mesh misalignment results. In contrast, non-parametric approaches directly regress human mesh vertices, resulting in pixel-aligned but unreasonable predictions. In this paper, we consider these two paradigms together for a better overall estimation. To this end, we propose a novel HYbrid REgressor (HYRE) that greatly benefits from the joint learning of both paradigms. The core of our HYRE is a hybrid intermediary across paradigms that provides complementary clues to each paradigm at the shared feature level and fuses their results at the part-based decision level, thereby bridging the gap between the two. We demonstrate the effectiveness of the proposed method through both quantitative and qualitative experimental analyses, resulting in improvements for each approach and ultimately leading to better hybrid results. Our experiments show that HYRE outperforms previous methods on challenging 3D human pose and shape benchmarks.
{"title":"HYRE: Hybrid Regressor for 3D Human Pose and Shape Estimation","authors":"Wenhao Li;Mengyuan Liu;Hong Liu;Bin Ren;Xia Li;Yingxuan You;Nicu Sebe","doi":"10.1109/TIP.2024.3515872","DOIUrl":"10.1109/TIP.2024.3515872","url":null,"abstract":"Regression-based 3D human pose and shape estimation often fall into one of two different paradigms. Parametric approaches, which regress the parameters of a human body model, tend to produce physically plausible but image-mesh misalignment results. In contrast, non-parametric approaches directly regress human mesh vertices, resulting in pixel-aligned but unreasonable predictions. In this paper, we consider these two paradigms together for a better overall estimation. To this end, we propose a novel HYbrid REgressor (HYRE) that greatly benefits from the joint learning of both paradigms. The core of our HYRE is a hybrid intermediary across paradigms that provides complementary clues to each paradigm at the shared feature level and fuses their results at the part-based decision level, thereby bridging the gap between the two. We demonstrate the effectiveness of the proposed method through both quantitative and qualitative experimental analyses, resulting in improvements for each approach and ultimately leading to better hybrid results. Our experiments show that HYRE outperforms previous methods on challenging 3D human pose and shape benchmarks.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"235-246"},"PeriodicalIF":0.0,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888260","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 : 2024-12-24DOI: 10.1109/TIP.2024.3519997
Chao Xie;Linfeng Fei;Huanjie Tao;Yaocong Hu;Wei Zhou;Jiun Tian Hoe;Weipeng Hu;Yap-Peng Tan
Recently, neural networks have become the dominant approach to low-light image enhancement (LLIE), with at least one-third of them adopting a Retinex-related architecture. However, through in-depth analysis, we contend that this most widely accepted LLIE structure is suboptimal, particularly when addressing the non-uniform illumination commonly observed in natural images. In this paper, we present a novel variant learning framework, termed residual quotient learning, to substantially alleviate this issue. Instead of following the existing Retinex-related decomposition-enhancement-reconstruction process, our basic idea is to explicitly reformulate the light enhancement task as adaptively predicting the latent quotient with reference to the original low-light input using a residual learning fashion. By leveraging the proposed residual quotient learning, we develop a lightweight yet effective network called ResQ-Net. This network features enhanced non-uniform illumination modeling capabilities, making it more suitable for real-world LLIE tasks. Moreover, due to its well-designed structure and reference-free loss function, ResQ-Net is flexible in training as it allows for zero-reference optimization, which further enhances the generalization and adaptability of our entire framework. Extensive experiments on various benchmark datasets demonstrate the merits and effectiveness of the proposed residual quotient learning, and our trained ResQ-Net outperforms state-of-the-art methods both qualitatively and quantitatively. Furthermore, a practical application in dark face detection is explored, and the preliminary results confirm the potential and feasibility of our method in real-world scenarios.
{"title":"Residual Quotient Learning for Zero-Reference Low-Light Image Enhancement","authors":"Chao Xie;Linfeng Fei;Huanjie Tao;Yaocong Hu;Wei Zhou;Jiun Tian Hoe;Weipeng Hu;Yap-Peng Tan","doi":"10.1109/TIP.2024.3519997","DOIUrl":"10.1109/TIP.2024.3519997","url":null,"abstract":"Recently, neural networks have become the dominant approach to low-light image enhancement (LLIE), with at least one-third of them adopting a Retinex-related architecture. However, through in-depth analysis, we contend that this most widely accepted LLIE structure is suboptimal, particularly when addressing the non-uniform illumination commonly observed in natural images. In this paper, we present a novel variant learning framework, termed residual quotient learning, to substantially alleviate this issue. Instead of following the existing Retinex-related decomposition-enhancement-reconstruction process, our basic idea is to explicitly reformulate the light enhancement task as adaptively predicting the latent quotient with reference to the original low-light input using a residual learning fashion. By leveraging the proposed residual quotient learning, we develop a lightweight yet effective network called ResQ-Net. This network features enhanced non-uniform illumination modeling capabilities, making it more suitable for real-world LLIE tasks. Moreover, due to its well-designed structure and reference-free loss function, ResQ-Net is flexible in training as it allows for zero-reference optimization, which further enhances the generalization and adaptability of our entire framework. Extensive experiments on various benchmark datasets demonstrate the merits and effectiveness of the proposed residual quotient learning, and our trained ResQ-Net outperforms state-of-the-art methods both qualitatively and quantitatively. Furthermore, a practical application in dark face detection is explored, and the preliminary results confirm the potential and feasibility of our method in real-world scenarios.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"365-378"},"PeriodicalIF":0.0,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884230","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 : 2024-12-23DOI: 10.1109/TIP.2024.3518759
Yang Yang;Wenjuan Xi;Luping Zhou;Jinhui Tang
Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.
{"title":"Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation","authors":"Yang Yang;Wenjuan Xi;Luping Zhou;Jinhui Tang","doi":"10.1109/TIP.2024.3518759","DOIUrl":"10.1109/TIP.2024.3518759","url":null,"abstract":"Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6881-6892"},"PeriodicalIF":0.0,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879658","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 : 2024-12-23DOI: 10.1109/TIP.2024.3518097
Jiarui Zhang;Ruixu Geng;Xiaolong Du;Yan Chen;Houqiang Li;Yang Hu
Passive non-line-of-sight (NLOS) imaging has witnessed rapid development in recent years, due to its ability to image objects that are out of sight. The light transport condition plays an important role in this task since changing the conditions will lead to different imaging models. Existing learning-based NLOS methods usually train independent models for different light transport conditions, which is computationally inefficient and impairs the practicality of the models. In this work, we propose NLOS-LTM, a novel passive NLOS imaging method that effectively handles multiple light transport conditions with a single network. We achieve this by inferring a latent light transport representation from the projection image and using this representation to modulate the network that reconstructs the hidden image from the projection image. We train a light transport encoder together with a vector quantizer to obtain the light transport representation. To further regulate this representation, we jointly learn both the reconstruction network and the reprojection network during training. A set of light transport modulation blocks is used to modulate the two jointly trained networks in a multi-scale way. Extensive experiments on a large-scale passive NLOS dataset demonstrate the superiority of the proposed method. The code is available at https://github.com/JerryOctopus/NLOS-LTM.
{"title":"Passive Non-Line-of-Sight Imaging With Light Transport Modulation","authors":"Jiarui Zhang;Ruixu Geng;Xiaolong Du;Yan Chen;Houqiang Li;Yang Hu","doi":"10.1109/TIP.2024.3518097","DOIUrl":"10.1109/TIP.2024.3518097","url":null,"abstract":"Passive non-line-of-sight (NLOS) imaging has witnessed rapid development in recent years, due to its ability to image objects that are out of sight. The light transport condition plays an important role in this task since changing the conditions will lead to different imaging models. Existing learning-based NLOS methods usually train independent models for different light transport conditions, which is computationally inefficient and impairs the practicality of the models. In this work, we propose NLOS-LTM, a novel passive NLOS imaging method that effectively handles multiple light transport conditions with a single network. We achieve this by inferring a latent light transport representation from the projection image and using this representation to modulate the network that reconstructs the hidden image from the projection image. We train a light transport encoder together with a vector quantizer to obtain the light transport representation. To further regulate this representation, we jointly learn both the reconstruction network and the reprojection network during training. A set of light transport modulation blocks is used to modulate the two jointly trained networks in a multi-scale way. Extensive experiments on a large-scale passive NLOS dataset demonstrate the superiority of the proposed method. The code is available at <uri>https://github.com/JerryOctopus/NLOS-LTM</uri>.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"410-424"},"PeriodicalIF":0.0,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879933","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 : 2024-12-20DOI: 10.1109/TIP.2024.3518100
Zhao Wang;Bolin Chen;Shurun Wang;Shiqi Wang;Yan Ye;Siwei Ma
How to compress face video is a crucial problem for a series of online applications, such as video chat/conference, live broadcasting and remote education. Compared to other natural videos, these face-centric videos owning abundant structural information can be compactly represented and high-quality reconstructed via deep generative models, such that the promising compression performance can be achieved. However, the existing generative face video compression schemes are faced with the inconsistency between the 3D facial motion in the physical world and the face content evolution in the 2D view. To solve this drawback, we propose a 3D-Keypoint-and-2D-Motion based generative method for Face Video Compression, namely FVC-3K2M, which can well ensure perceptual compensation and visual consistency between motion description and face reconstruction. In particular, the temporal evolution of face video can be characterized into separate 3D keypoints from the global and local perspectives, entailing great coding flexibility and accurate motion representation. Moreover, a cascade motion conversion mechanism is further proposed to internally convert 3D keypoints to 2D dense motion, enforcing the face video reconstruction to be perceptually realistic. Finally, an adaptive reference frame selection scheme is developed to enhance the adaptation of various temporal movements. Experimental results show that the proposed scheme can realize reliable video communication in the extremely limited bandwidth, e.g., 2 kbps. Compared to the state-of-the-art video coding standards and the latest face video compression methods, extensive comparisons demonstrate that our proposed scheme achieves superior compression performance in terms of multiple quality evaluations.
{"title":"Ultra-Low Bitrate Face Video Compression Based on Conversions From 3D Keypoints to 2D Motion Map","authors":"Zhao Wang;Bolin Chen;Shurun Wang;Shiqi Wang;Yan Ye;Siwei Ma","doi":"10.1109/TIP.2024.3518100","DOIUrl":"10.1109/TIP.2024.3518100","url":null,"abstract":"How to compress face video is a crucial problem for a series of online applications, such as video chat/conference, live broadcasting and remote education. Compared to other natural videos, these face-centric videos owning abundant structural information can be compactly represented and high-quality reconstructed via deep generative models, such that the promising compression performance can be achieved. However, the existing generative face video compression schemes are faced with the inconsistency between the 3D facial motion in the physical world and the face content evolution in the 2D view. To solve this drawback, we propose a 3D-Keypoint-and-2D-Motion based generative method for Face Video Compression, namely FVC-3K2M, which can well ensure perceptual compensation and visual consistency between motion description and face reconstruction. In particular, the temporal evolution of face video can be characterized into separate 3D keypoints from the global and local perspectives, entailing great coding flexibility and accurate motion representation. Moreover, a cascade motion conversion mechanism is further proposed to internally convert 3D keypoints to 2D dense motion, enforcing the face video reconstruction to be perceptually realistic. Finally, an adaptive reference frame selection scheme is developed to enhance the adaptation of various temporal movements. Experimental results show that the proposed scheme can realize reliable video communication in the extremely limited bandwidth, e.g., 2 kbps. Compared to the state-of-the-art video coding standards and the latest face video compression methods, extensive comparisons demonstrate that our proposed scheme achieves superior compression performance in terms of multiple quality evaluations.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6850-6864"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867126","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 : 2024-12-20DOI: 10.1109/TIP.2024.3515873
Yuzhi Zhao;Lai-Man Po;Xin Ye;Yongzhe Xu;Qiong Yan
Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at https://github.com/zhaoyuzhi/QRNet.
{"title":"Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring","authors":"Yuzhi Zhao;Lai-Man Po;Xin Ye;Yongzhe Xu;Qiong Yan","doi":"10.1109/TIP.2024.3515873","DOIUrl":"10.1109/TIP.2024.3515873","url":null,"abstract":"Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at <uri>https://github.com/zhaoyuzhi/QRNet</uri>.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"350-364"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867124","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：