Yuming Fang

Wei Shang, Dongwei Ren, Wanying Zhang et al.

Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we first describe a strong baseline for AVSR by putting together three variants of elementary building blocks: 1) a flow-guided recurrent unit that aggregates spatiotemporal information from previous frames, 2) a flow-refined cross-attention unit that selects spatiotemporal information from future frames, and 3) a hyper-upsampling unit that generates scaleaware and content-independent upsampling kernels. We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network. This prior has proven effective in discriminating structure and texture across different locations and scales, which is beneficial for AVSR. Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart. The code is available at https://github.com/shangwei5/ST-AVSR.

Zhihua Wang, Keshuo Xu, Yang Yang et al.

Measuring perceptual color differences (CDs) is of great importance in modern smartphone photography. Despite the long history, most CD measures have been constrained by psychophysical data of homogeneous color patches or a limited number of simplistic natural photographic images. It is thus questionable whether existing CD measures generalize in the age of smartphone photography characterized by greater content complexities and learning-based image signal processors. In this paper, we put together so far the largest image dataset for perceptual CD assessment, in which the photographic images are 1) captured by six flagship smartphones, 2) altered by Photoshop, 3) post-processed by built-in filters of the smartphones, and 4) reproduced with incorrect color profiles. We then conduct a large-scale psychophysical experiment to gather perceptual CDs of 30,000 image pairs in a carefully controlled laboratory environment. Based on the newly established dataset, we make one of the first attempts to construct an end-to-end learnable CD formula based on a lightweight neural network, as a generalization of several previous metrics. Extensive experiments demonstrate that the optimized formula outperforms 33 existing CD measures by a large margin, offers reasonable local CD maps without the use of dense supervision, generalizes well to homogeneous color patch data, and empirically behaves as a proper metric in the mathematical sense. Our dataset and code are publicly available at https://github.com/hellooks/CDNet.

Xiaoshui Huang, Wentao Qu, Yifan Zuo et al.

Rejecting correspondence outliers enables to boost the correspondence quality, which is a critical step in achieving high point cloud registration accuracy. The current state-of-the-art correspondence outlier rejection methods only utilize the structure features of the correspondences. However, texture information is critical to reject the correspondence outliers in our human vision system. In this paper, we propose General Multimodal Fusion (GMF) to learn to reject the correspondence outliers by leveraging both the structure and texture information. Specifically, two cross-attention-based fusion layers are proposed to fuse the texture information from paired images and structure information from point correspondences. Moreover, we propose a convolutional position encoding layer to enhance the difference between Tokens and enable the encoding feature pay attention to neighbor information. Our position encoding layer will make the cross-attention operation integrate both local and global information. Experiments on multiple datasets(3DMatch, 3DLoMatch, KITTI) and recent state-of-the-art models (3DRegNet, DGR, PointDSC) prove that our GMF achieves wide generalization ability and consistently improves the point cloud registration accuracy. Furthermore, several ablation studies demonstrate the robustness of the proposed GMF on different loss functions, lighting conditions and noises.The code is available at https://github.com/XiaoshuiHuang/GMF.

Wen Wen, Mu Li, Yiru Yao et al.

Investigating how people perceive virtual reality (VR) videos in the wild (i.e., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortions localized in space and time. Existing panoramic video databases only consider synthetic distortions, assume fixed viewing conditions, and are limited in size. To overcome these shortcomings, we construct the VR Video Quality in the Wild (VRVQW) database, containing $502$ user-generated videos with diverse content and distortion characteristics. Based on VRVQW, we conduct a formal psychophysical experiment to record the scanpaths and perceived quality scores from $139$ participants under two different viewing conditions. We provide a thorough statistical analysis of the recorded data, observing significant impact of viewing conditions on both human scanpaths and perceived quality. Moreover, we develop an objective quality assessment model for VR videos based on pseudocylindrical representation and convolution. Results on the proposed VRVQW show that our method is superior to existing video quality assessment models. We have made the database and code available at https://github.com/limuhit/VR-Video-Quality-in-the-Wild.

Jingwen Hou, Henghui Ding, Weisi Lin et al.

In this work, we point out that the major dilemma of image aesthetics assessment (IAA) comes from the abstract nature of aesthetic labels. That is, a vast variety of distinct contents can correspond to the same aesthetic label. On the one hand, during inference, the IAA model is required to relate various distinct contents to the same aesthetic label. On the other hand, when training, it would be hard for the IAA model to learn to distinguish different contents merely with the supervision from aesthetic labels, since aesthetic labels are not directly related to any specific content. To deal with this dilemma, we propose to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model. Expecting the combination of multiple POC models can provide sufficient knowledge on various image contents, the IAA model can easier learn to relate various distinct contents to a limited number of aesthetic labels. By supervising an end-to-end single-backbone IAA model with the distilled knowledge, the performance of the IAA model is significantly improved by 4.8% in SRCC compared to the version trained only with ground-truth aesthetic labels. On specific categories of images, the SRCC improvement brought by the proposed method can achieve up to 7.2%. Peer comparison also shows that our method outperforms 10 previous IAA methods.

Xiangjie Sui, Hanwei Zhu, Xuelin Liu et al.

Despite substantial efforts dedicated to the design of heuristic models for omnidirectional (i.e., 360$^\circ$) image quality assessment (OIQA), a conspicuous gap remains due to the lack of consideration for the diversity of viewing behaviors that leads to the varying perceptual quality of 360$^\circ$ images. Two critical aspects underline this oversight: the neglect of viewing conditions that significantly sway user gaze patterns and the overreliance on a single viewport sequence from the 360$^\circ$ image for quality inference. To address these issues, we introduce a unique generative scanpath representation (GSR) for effective quality inference of 360$^\circ$ images, which aggregates varied perceptual experiences of multi-hypothesis users under a predefined viewing condition. More specifically, given a viewing condition characterized by the starting point of viewing and exploration time, a set of scanpaths consisting of dynamic visual fixations can be produced using an apt scanpath generator. Following this vein, we use the scanpaths to convert the 360$^\circ$ image into the unique GSR, which provides a global overview of gazed-focused contents derived from scanpaths. As such, the quality inference of the 360$^\circ$ image is swiftly transformed to that of GSR. We then propose an efficient OIQA computational framework by learning the quality maps of GSR. Comprehensive experimental results validate that the predictions of the proposed framework are highly consistent with human perception in the spatiotemporal domain, especially in the challenging context of locally distorted 360$^\circ$ images under varied viewing conditions. The code will be released at https://github.com/xiangjieSui/GSR

Yifan Zuo, Jiacheng Xie, Yuming Fang et al.

A mainstream type of the state of the arts (SOTAs) based on convolutional neural network (CNN) for real image denoising contains two sub-problems, i.e., noise estimation and non-blind denoising. This paper considers real noise approximated by heteroscedastic Gaussian/Poisson Gaussian distributions with in-camera signal processing pipelines. The related works always exploit the estimated noise prior via channel-wise concatenation followed by a convolutional layer with spatially sharing kernels. Due to the variable modes of noise strength and frequency details of all feature positions, this design cannot adaptively tune the corresponding denoising patterns. To address this problem, we propose a novel conditional filter in which the optimal kernels for different feature positions can be adaptively inferred by local features from the image and the noise map. Also, we bring the thought that alternatively performs noise estimation and non-blind denoising into CNN structure, which continuously updates noise prior to guide the iterative feature denoising. In addition, according to the property of heteroscedastic Gaussian distribution, a novel affine transform block is designed to predict the stationary noise component and the signal-dependent noise component. Compared with SOTAs, extensive experiments are conducted on five synthetic datasets and three real datasets, which shows the improvement of the proposed CFNet.

Chenglizhao Chen, Hengsen Wang, Yuming Fang et al.

The existing state-of-the-art (SOTA) video salient object detection (VSOD) models have widely followed short-term methodology, which dynamically determines the balance between spatial and temporal saliency fusion by solely considering the current consecutive limited frames. However, the short-term methodology has one critical limitation, which conflicts with the real mechanism of our visual system -- a typical long-term methodology. As a result, failure cases keep showing up in the results of the current SOTA models, and the short-term methodology becomes the major technical bottleneck. To solve this problem, this paper proposes a novel VSOD approach, which performs VSOD in a complete long-term way. Our approach converts the sequential VSOD, a sequential task, to a data mining problem, i.e., decomposing the input video sequence to object proposals in advance and then mining salient object proposals as much as possible in an easy-to-hard way. Since all object proposals are simultaneously available, the proposed approach is a complete long-term approach, which can alleviate some difficulties rooted in conventional short-term approaches. In addition, we devised an online updating scheme that can grasp the most representative and trustworthy pattern profile of the salient objects, outputting framewise saliency maps with rich details and smoothing both spatially and temporally. The proposed approach outperforms almost all SOTA models on five widely used benchmark datasets.

Weide Liu, Zhonghua Wu, Yang Zhao et al.

Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.

Jiaqi He, Zhihua Wang, Leon Wang et al.

Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures inadequately capture the human color perception of misaligned image pairs, which are prevalent in digital photography (e.g., the same scene captured by different smartphones). In this paper, we describe a perceptual CD measure based on the multiscale sliced Wasserstein distance, which facilitates efficient comparisons between non-local patches of similar color and structure. This aligns with the modern understanding of color perception, where color and structure are inextricably interdependent as a unitary process of perceptual organization. Meanwhile, our method is easy to implement and training-free. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images, and consistently surpasses competing models in the presence of image misalignment. Additionally, we empirically verify that our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks. The code is available at https://github.com/real-hjq/MS-SWD.

Xue Xia, Kun Zhan, Yuming Fang et al.

Deep learning brought boosts to auto diabetic retinopathy (DR) diagnosis, thus, greatly helping ophthalmologists for early disease detection, which contributes to preventing disease deterioration that may eventually lead to blindness. It has been proved that convolutional neural network (CNN)-aided lesion identifying or segmentation benefits auto DR screening. The key to fine-grained lesion tasks mainly lies in: (1) extracting features being both sensitive to tiny lesions and robust against DR-irrelevant interference, and (2) exploiting and re-using encoded information to restore lesion locations under extremely imbalanced data distribution. To this end, we propose a CNN-based DR diagnosis network with attention mechanism involved, termed lesion-aware network, to better capture lesion information from imbalanced data. Specifically, we design the lesion-aware module (LAM) to capture noise-like lesion areas across deeper layers, and the feature-preserve module (FPM) to assist shallow-to-deep feature fusion. Afterward, the proposed lesion-aware network (LANet) is constructed by embedding the LAM and FPM into the CNN decoders for DR-related information utilization. The proposed LANet is then further extended to a DR screening network by adding a classification layer. Through experiments on three public fundus datasets with pixel-level annotations, our method outperforms the mainstream methods with an area under curve of 0.967 in DR screening, and increases the overall average precision by 7.6%, 2.1%, and 1.2% in lesion segmentation on three datasets. Besides, the ablation study validates the effectiveness of the proposed sub-modules.

Peibei Cao, Chenyang Le, Yuming Fang et al.

With the increasing popularity and accessibility of high dynamic range (HDR) photography, tone mapping operators (TMOs) for dynamic range compression are practically demanding. In this paper, we develop a two-stage neural network-based TMO that is self-calibrated and perceptually optimized. In Stage one, motivated by the physiology of the early stages of the human visual system, we first decompose an HDR image into a normalized Laplacian pyramid. We then use two lightweight deep neural networks (DNNs), taking the normalized representation as input and estimating the Laplacian pyramid of the corresponding LDR image. We optimize the tone mapping network by minimizing the normalized Laplacian pyramid distance (NLPD), a perceptual metric aligning with human judgments of tone-mapped image quality. In Stage two, the input HDR image is self-calibrated to compute the final LDR image. We feed the same HDR image but rescaled with different maximum luminances to the learned tone mapping network, and generate a pseudo-multi-exposure image stack with different detail visibility and color saturation. We then train another lightweight DNN to fuse the LDR image stack into a desired LDR image by maximizing a variant of the structural similarity index for multi-exposure image fusion (MEF-SSIM), which has been proven perceptually relevant to fused image quality. The proposed self-calibration mechanism through MEF enables our TMO to accept uncalibrated HDR images, while being physiology-driven. Extensive experiments show that our method produces images with consistently better visual quality. Additionally, since our method builds upon three lightweight DNNs, it is among the fastest local TMOs.

Xiaoshui Huang, Tianlin Zhu, Yifan Zuo et al.

Single-cell RNA sequencing (scRNA-seq) is essential for decoding tumor heterogeneity. However, pan-cancer research still faces two key challenges: learning discriminative and efficient single-cell representations, and establishing a comprehensive evaluation benchmark. In this paper, we introduce PanFoMa, a lightweight hybrid neural network that combines the strengths of Transformers and state-space models to achieve a balance between performance and efficiency. PanFoMa consists of a front-end local-context encoder with shared self-attention layers to capture complex, order-independent gene interactions; and a back-end global sequential feature decoder that efficiently integrates global context using a linear-time state-space model. This modular design preserves the expressive power of Transformers while leveraging the scalability of Mamba to enable transcriptome modeling, effectively capturing both local and global regulatory signals. To enable robust evaluation, we also construct a large-scale pan-cancer single-cell benchmark, PanFoMaBench, containing over 3.5 million high-quality cells across 33 cancer subtypes, curated through a rigorous preprocessing pipeline. Experimental results show that PanFoMa outperforms state-of-the-art models on our pan-cancer benchmark (+4.0\%) and across multiple public tasks, including cell type annotation (+7.4\%), batch integration (+4.0\%) and multi-omics integration (+3.1\%). The code is available at https://github.com/Xiaoshui-Huang/PanFoMa.

Weide Liu, Xiaoyang Zhong, Jingwen Hou et al.

Multimodal Named Entity Recognition (MNER) is a crucial task for information extraction from social media platforms such as Twitter. Most current methods rely on attention weights to extract information from both text and images but are often unreliable and lack interpretability. To address this problem, we propose incorporating uncertainty estimation into the MNER task, producing trustworthy predictions. Our proposed algorithm models the distribution of each modality as a Normal-inverse Gamma distribution, and fuses them into a unified distribution with an evidential fusion mechanism, enabling hierarchical characterization of uncertainties and promotion of prediction accuracy and trustworthiness. Additionally, we explore the potential of pre-trained large foundation models in MNER and propose an efficient fusion approach that leverages their robust feature representations. Experiments on two datasets demonstrate that our proposed method outperforms the baselines and achieves new state-of-the-art performance.

Hanwei Zhu, Xiangjie Sui, Baoliang Chen et al.

While abundant research has been conducted on improving high-level visual understanding and reasoning capabilities of large multimodal models~(LMMs), their visual quality assessment~(IQA) ability has been relatively under-explored. Here we take initial steps towards this goal by employing the two-alternative forced choice~(2AFC) prompting, as 2AFC is widely regarded as the most reliable way of collecting human opinions of visual quality. Subsequently, the global quality score of each image estimated by a particular LMM can be efficiently aggregated using the maximum a posterior estimation. Meanwhile, we introduce three evaluation criteria: consistency, accuracy, and correlation, to provide comprehensive quantifications and deeper insights into the IQA capability of five LMMs. Extensive experiments show that existing LMMs exhibit remarkable IQA ability on coarse-grained quality comparison, but there is room for improvement on fine-grained quality discrimination. The proposed dataset sheds light on the future development of IQA models based on LMMs. The codes will be made publicly available at https://github.com/h4nwei/2AFC-LMMs.

Jiebin Yan, Jiale Rao, Xuelin Liu et al.

Omnidirectional image quality assessment (OIQA) has been one of the hot topics in IQA with the continuous development of VR techniques, and achieved much success in the past few years. However, most studies devote themselves to the uniform distortion issue, i.e., all regions of an omnidirectional image are perturbed by the ``same amount'' of noise, while ignoring the non-uniform distortion issue, i.e., partial regions undergo ``different amount'' of perturbation with the other regions in the same omnidirectional image. Additionally, nearly all OIQA models are verified on the platforms containing a limited number of samples, which largely increases the over-fitting risk and therefore impedes the development of OIQA. To alleviate these issues, we elaborately explore this topic from both subjective and objective perspectives. Specifically, we construct a large OIQA database containing 10,320 non-uniformly distorted omnidirectional images, each of which is generated by considering quality impairments on one or two camera len(s). Then we meticulously conduct psychophysical experiments and delve into the influence of both holistic and individual factors (i.e., distortion range and viewing condition) on omnidirectional image quality. Furthermore, we propose a perception-guided OIQA model for non-uniform distortion by adaptively simulating users' viewing behavior. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods. The source code is available at https://github.com/RJL2000/OIQAND.

Jiebin Yan, Jiale Rao, Junjie Chen et al.

Omnidirectional image quality assessment (OIQA) has been widely investigated in the past few years and achieved much success. However, most of existing studies are dedicated to solve the uniform distortion problem in OIQA, which has a natural gap with the non-uniform distortion problem, and their ability in capturing non-uniform distortion is far from satisfactory. To narrow this gap, in this paper, we propose a multitask auxiliary network for non-uniformly distorted omnidirectional images, where the parameters are optimized by jointly training the main task and other auxiliary tasks. The proposed network mainly consists of three parts: a backbone for extracting multiscale features from the viewport sequence, a multitask feature selection module for dynamically allocating specific features to different tasks, and auxiliary sub-networks for guiding the proposed model to capture local distortion and global quality change. Extensive experiments conducted on two large-scale OIQA databases demonstrate that the proposed model outperforms other state-of-the-art OIQA metrics, and these auxiliary sub-networks contribute to improve the performance of the proposed model. The source code is available at https://github.com/RJL2000/MTAOIQA.

Jiebin Yan, Ziwen Tan, Yuming Fang et al.

Omnidirectional image, also called 360-degree image, is able to capture the entire 360-degree scene, thereby providing more realistic immersive feelings for users than general 2D image and stereoscopic image. Meanwhile, this feature brings great challenges to measuring the perceptual quality of omnidirectional images, which is closely related to users' quality of experience, especially when the omnidirectional images suffer from non-uniform distortion. In this paper, we propose a novel and effective blind omnidirectional image quality assessment (BOIQA) model with multi-axis attention (Max360IQ), which can proficiently measure not only the quality of uniformly distorted omnidirectional images but also the quality of non-uniformly distorted omnidirectional images. Specifically, the proposed Max360IQ is mainly composed of a backbone with stacked multi-axis attention modules for capturing both global and local spatial interactions of extracted viewports, a multi-scale feature integration (MSFI) module to fuse multi-scale features and a quality regression module with deep semantic guidance for predicting the quality of omnidirectional images. Experimental results demonstrate that the proposed Max360IQ outperforms the state-of-the-art Assessor360 by 3.6\% in terms of SRCC on the JUFE database with non-uniform distortion, and gains improvement of 0.4\% and 0.8\% in terms of SRCC on the OIQA and CVIQ databases, respectively. The source code is available at https://github.com/WenJuing/Max360IQ.

Junjie Chen, Weilong Chen, Yifan Zuo et al.

Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling, and obtain interacted features from support and query via cross-attention. Hence, these works neglect to mine fine-grained and structure-aware (FGSA) features from both support and query images, which are crucial for pixel-level keypoint localization. To this end, we propose a novel yet concise framework, which recurrently mines FGSA features from both support and query images. Specifically, we design a FGSA mining module based on deformable attention mechanism. On the one hand, we mine fine-grained features by applying deformable attention head over multi-scale feature maps. On the other hand, we mine structure-aware features by offsetting the reference points of keypoints to their linked keypoints. By means of above module, we recurrently mine FGSA features from support and query images, and thus obtain better support features and query estimations. In addition, we propose to use mixup keypoints to pad various classes to a unified keypoint number, which could provide richer supervision than the zero padding used in existing works. We conduct extensive experiments and in-depth studies on large-scale MP-100 dataset, and outperform SOTA method dramatically (+3.2\%PCK@0.05). Code is avaiable at https://github.com/chenbys/FMMP.

Boyang Wan, Wenhui Jiang, Yuming Fang et al.

Anomaly detection has attracted considerable search attention. However, existing anomaly detection databases encounter two major problems. Firstly, they are limited in scale. Secondly, training sets contain only video-level labels indicating the existence of an abnormal event during the full video while lacking annotations of precise time durations. To tackle these problems, we contribute a new Large-scale Anomaly Detection (LAD) database as the benchmark for anomaly detection in video sequences, which is featured in two aspects. 1) It contains 2000 video sequences including normal and abnormal video clips with 14 anomaly categories including crash, fire, violence, etc. with large scene varieties, making it the largest anomaly analysis database to date. 2) It provides the annotation data, including video-level labels (abnormal/normal video, anomaly type) and frame-level labels (abnormal/normal video frame) to facilitate anomaly detection. Leveraging the above benefits from the LAD database, we further formulate anomaly detection as a fully-supervised learning problem and propose a multi-task deep neural network to solve it. We first obtain the local spatiotemporal contextual feature by using an Inflated 3D convolutional (I3D) network. Then we construct a recurrent convolutional neural network fed the local spatiotemporal contextual feature to extract the spatiotemporal contextual feature. With the global spatiotemporal contextual feature, the anomaly type and score can be computed simultaneously by a multi-task neural network. Experimental results show that the proposed method outperforms the state-of-the-art anomaly detection methods on our database and other public databases of anomaly detection. Codes are available at https://github.com/wanboyang/anomaly_detection_LAD2000.

Jiebin Yan, Yu Zhong, Yuming Fang et al.

Semantic segmentation is an extensively studied task in computer vision, with numerous methods proposed every year. Thanks to the advent of deep learning in semantic segmentation, the performance on existing benchmarks is close to saturation. A natural question then arises: Does the superior performance on the closed (and frequently re-used) test sets transfer to the open visual world with unconstrained variations? In this paper, we take steps toward answering the question by exposing failures of existing semantic segmentation methods in the open visual world under the constraint of very limited human labeling effort. Inspired by previous research on model falsification, we start from an arbitrarily large image set, and automatically sample a small image set by MAximizing the Discrepancy (MAD) between two segmentation methods. The selected images have the greatest potential in falsifying either (or both) of the two methods. We also explicitly enforce several conditions to diversify the exposed failures, corresponding to different underlying root causes. A segmentation method, whose failures are more difficult to be exposed in the MAD competition, is considered better. We conduct a thorough MAD diagnosis of ten PASCAL VOC semantic segmentation algorithms. With detailed analysis of experimental results, we point out strengths and weaknesses of the competing algorithms, as well as potential research directions for further advancement in semantic segmentation. The codes are publicly available at \url{https://github.com/QTJiebin/MAD_Segmentation}.

Qijian Zhang, Runmin Cong, Chongyi Li et al.

Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem. In this paper, we propose an end-to-end Dense Attention Fluid Network (DAFNet) for SOD in optical RSIs. A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships, and is further embedded in a Dense Attention Fluid (DAF) structure that enables shallow attention cues flow into deep layers to guide the generation of high-level feature attention maps. Specifically, the GCA module is composed of two key components, where the global feature aggregation module achieves mutual reinforcement of salient feature embeddings from any two spatial locations, and the cascaded pyramid attention module tackles the scale variation issue by building up a cascaded pyramid framework to progressively refine the attention map in a coarse-to-fine manner. In addition, we construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations, which is currently the largest publicly available benchmark. Extensive experiments demonstrate that our proposed DAFNet significantly outperforms the existing state-of-the-art SOD competitors. https://github.com/rmcong/DAFNet_TIP20

Junjie Chen, Jiebin Yan, Yuming Fang et al.

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE. Considering that human can quickly perceive potential keypoints of arbitrary objects, we propose a novel framework for CAPE based on such potential keypoints (named as meta-points). Specifically, we maintain learnable embeddings to capture inherent information of various keypoints, which interact with image feature maps to produce meta-points without any support. The produced meta-points could serve as meaningful potential keypoints for CAPE. Due to the inevitable gap between inherency and annotation, we finally utilize the identities and details offered by support keypoints to assign and refine meta-points to desired keypoints in query image. In addition, we propose a progressive deformable point decoder and a slacked regression loss for better prediction and supervision. Our novel framework not only reveals the inherency of keypoints but also outperforms existing methods of CAPE. Comprehensive experiments and in-depth studies on large-scale MP-100 dataset demonstrate the effectiveness of our framework.

Jiebin Yan, Lei Wu, Yuming Fang et al.

With the rapid development of multimedia processing and deep learning technologies, especially in the field of video understanding, video quality assessment (VQA) has achieved significant progress. Although researchers have moved from designing efficient video quality mapping models to various research directions, in-depth exploration of the effectiveness-efficiency trade-offs of spatio-temporal modeling in VQA models is still less sufficient. Considering the fact that videos have highly redundant information, this paper investigates this problem from the perspective of joint spatial and temporal sampling, aiming to seek the answer to how little information we should keep at least when feeding videos into the VQA models while with acceptable performance sacrifice. To this end, we drastically sample the video's information from both spatial and temporal dimensions, and the heavily squeezed video is then fed into a stable VQA model. Comprehensive experiments regarding joint spatial and temporal sampling are conducted on six public video quality databases, and the results demonstrate the acceptable performance of the VQA model when throwing away most of the video information. Furthermore, with the proposed joint spatial and temporal sampling strategy, we make an initial attempt to design an online VQA model, which is instantiated by as simple as possible a spatial feature extractor, a temporal feature fusion module, and a global quality regression module. Through quantitative and qualitative experiments, we verify the feasibility of online VQA model by simplifying itself and reducing input.

Xiaoshui Huang, Zhou Huang, Yifan Zuo et al.

The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distinguishing the ambiguous structures in the overlapping regions. Therefore, the ambiguous features they extracted resulted in a significant number of outlier matches from overlapping regions. To solve this problem, we propose a prior-guided SMoE-based registration method to improve the feature distinctiveness by dispatching the potential correspondences to the same experts. Specifically, we propose a prior-guided SMoE module by fusing prior overlap and potential correspondence embeddings for routing, assigning tokens to the most suitable experts for processing. In addition, we propose a registration framework by a specific combination of Transformer layer and prior-guided SMoE module. The proposed method not only pays attention to the importance of locating the overlapping areas of point clouds, but also commits to finding more accurate correspondences in overlapping areas. Our extensive experiments demonstrate the effectiveness of our method, achieving state-of-the-art registration recall (95.7\%/79.3\%) on the 3DMatch/3DLoMatch benchmark. Moreover, we also test the performance on ModelNet40 and demonstrate excellent performance.

Kun Xu, Yushu Zhang, Shuren Qi et al.

The task of text-to-image generation has achieved tremendous success in practice, with emerging concept generation models capable of producing highly personalized and customized content. Fervor for concept generation is increasing rapidly among users, and platforms for concept sharing have sprung up. The concept owners may upload malicious concepts and disguise them with non-malicious text descriptions and example images to deceive users into downloading and generating malicious content. The platform needs a quick method to determine whether a concept is malicious to prevent the spread of malicious concepts. However, simply relying on concept image generation to judge whether a concept is malicious requires time and computational resources. Especially, as the number of concepts uploaded and downloaded on the platform continues to increase, this approach becomes impractical and poses a risk of generating malicious content. In this paper, we propose Concept QuickLook, the first systematic work to incorporate malicious concept detection into research, which performs detection based solely on concept files without generating any images. We define malicious concepts and design two work modes for detection: concept matching and fuzzy detection. Extensive experiments demonstrate that the proposed Concept QuickLook can detect malicious concepts and demonstrate practicality in concept sharing platforms. We also design robustness experiments to further validate the effectiveness of the solution. We hope this work can initiate malicious concept detection tasks and provide some inspiration.

Zhihua Wang, Yu Long, Qinghua Lin et al.

Deep neural networks (DNNs) have recently become the leading method for low-light image enhancement (LLIE). However, despite significant progress, their outputs may still exhibit issues such as amplified noise, incorrect white balance, or unnatural enhancements when deployed in real world applications. A key challenge is the lack of diverse, large scale training data that captures the complexities of low-light conditions and imaging pipelines. In this paper, we propose a novel image signal processing (ISP) driven data synthesis pipeline that addresses these challenges by generating unlimited paired training data. Specifically, our pipeline begins with easily collected high-quality normal-light images, which are first unprocessed into the RAW format using a reverse ISP. We then synthesize low-light degradations directly in the RAW domain. The resulting data is subsequently processed through a series of ISP stages, including white balance adjustment, color space conversion, tone mapping, and gamma correction, with controlled variations introduced at each stage. This broadens the degradation space and enhances the diversity of the training data, enabling the generated data to capture a wide range of degradations and the complexities inherent in the ISP pipeline. To demonstrate the effectiveness of our synthetic pipeline, we conduct extensive experiments using a vanilla UNet model consisting solely of convolutional layers, group normalization, GeLU activation, and convolutional block attention modules (CBAMs). Extensive testing across multiple datasets reveals that the vanilla UNet model trained with our data synthesis pipeline delivers high fidelity, visually appealing enhancement results, surpassing state-of-the-art (SOTA) methods both quantitatively and qualitatively.

Jiebin Yan, Ziwen Tan, Jiale Rao et al.

Blind panoramic image quality assessment (BPIQA) has recently brought new challenge to the visual quality community, due to the complex interaction between immersive content and human behavior. Although many efforts have been made to advance BPIQA from both conducting psychophysical experiments and designing performance-driven objective algorithms, \textit{limited content} and \textit{few samples} in those closed sets inevitably would result in shaky conclusions, thereby hindering the development of BPIQA, we refer to it as the \textit{easy-database} issue. In this paper, we present a sufficient computational analysis of degradation modeling in BPIQA to thoroughly explore the \textit{easy-database issue}, where we carefully design three types of experiments via investigating the gap between BPIQA and blind image quality assessment (BIQA), the necessity of specific design in BPIQA models, and the generalization ability of BPIQA models. From extensive experiments, we find that easy databases narrow the gap between the performance of BPIQA and BIQA models, which is unconducive to the development of BPIQA. And the easy databases make the BPIQA models be closed to saturation, therefore the effectiveness of the associated specific designs can not be well verified. Besides, the BPIQA models trained on our recently proposed databases with complicated degradation show better generalization ability. Thus, we believe that much more efforts are highly desired to put into BPIQA from both subjective viewpoint and objective viewpoint.

Weide Liu, Jingwen Hou, Xiaoyang Zhong et al.

Deep learning-based brain tumor segmentation (BTS) models for multi-modal MRI images have seen significant advancements in recent years. However, a common problem in practice is the unavailability of some modalities due to varying scanning protocols and patient conditions, making segmentation from incomplete MRI modalities a challenging issue. Previous methods have attempted to address this by fusing accessible multi-modal features, leveraging attention mechanisms, and synthesizing missing modalities using generative models. However, these methods ignore the intrinsic problems of medical image segmentation, such as the limited availability of training samples, particularly for cases with tumors. Furthermore, these methods require training and deploying a specific model for each subset of missing modalities. To address these issues, we propose a novel approach that enhances the BTS model from two perspectives. Firstly, we introduce a pre-training stage that generates a diverse pre-training dataset covering a wide range of different combinations of tumor shapes and brain anatomy. Secondly, we propose a post-training stage that enables the model to reconstruct missing modalities in the prediction results when only partial modalities are available. To achieve the pre-training stage, we conceptually decouple the MRI image into two parts: `anatomy' and `tumor'. We pre-train the BTS model using synthesized data generated from the anatomy and tumor parts across different training samples. ... Extensive experiments demonstrate that our proposed method significantly improves the performance over the baseline and achieves new state-of-the-art results on three brain tumor segmentation datasets: BRATS2020, BRATS2018, and BRATS2015.

Xiaoshui Huang, Wentao Qu, Yifan Zuo et al.

The existing state-of-the-art point descriptor relies on structure information only, which omit the texture information. However, texture information is crucial for our humans to distinguish a scene part. Moreover, the current learning-based point descriptors are all black boxes which are unclear how the original points contribute to the final descriptor. In this paper, we propose a new multimodal fusion method to generate a point cloud registration descriptor by considering both structure and texture information. Specifically, a novel attention-fusion module is designed to extract the weighted texture information for the descriptor extraction. In addition, we propose an interpretable module to explain the original points in contributing to the final descriptor. We use the descriptor element as the loss to backpropagate to the target layer and consider the gradient as the significance of this point to the final descriptor. This paper moves one step further to explainable deep learning in the registration task. Comprehensive experiments on 3DMatch, 3DLoMatch and KITTI demonstrate that the multimodal fusion descriptor achieves state-of-the-art accuracy and improve the descriptor's distinctiveness. We also demonstrate that our interpretable module in explaining the registration descriptor extraction.

Kede Ma, Yuming Fang

This tutorial provides the audience with the basic theories, methodologies, and current progresses of image quality assessment (IQA). From an actionable perspective, we will first revisit several subjective quality assessment methodologies, with emphasis on how to properly select visual stimuli. We will then present in detail the design principles of objective quality assessment models, supplemented by an in-depth analysis of their advantages and disadvantages. Both hand-engineered and (deep) learning-based methods will be covered. Moreover, the limitations with the conventional model comparison methodology for objective quality models will be pointed out, and novel comparison methodologies such as those based on the theory of "analysis by synthesis" will be introduced. We will last discuss the real-world multimedia applications of IQA, and give a list of open challenging problems, in the hope of encouraging more and more talented researchers and engineers devoting to this exciting and rewarding research field.

Chenyang Le, Jiebin Yan, Yuming Fang et al.

We describe a deep high-dynamic-range (HDR) image tone mapping operator that is computationally efficient and perceptually optimized. We first decompose an HDR image into a normalized Laplacian pyramid, and use two deep neural networks (DNNs) to estimate the Laplacian pyramid of the desired tone-mapped image from the normalized representation. We then end-to-end optimize the entire method over a database of HDR images by minimizing the normalized Laplacian pyramid distance (NLPD), a recently proposed perceptual metric. Qualitative and quantitative experiments demonstrate that our method produces images with better visual quality, and runs the fastest among existing local tone mapping algorithms.

Zhihua Wang, Zhi-Ri Tang, Jianguo Zhang et al.

Nowadays, most existing blind image quality assessment (BIQA) models 1) are developed for synthetically-distorted images and often generalize poorly to authentic ones; 2) heavily rely on human ratings, which are prohibitively labor-expensive to collect. Here, we propose an $opinion$-$free$ BIQA method that learns from synthetically-distorted images and multiple agents to assess the perceptual quality of authentically-distorted ones captured in the wild without relying on human labels. Specifically, we first assemble a large number of image pairs from synthetically-distorted images and use a set of full-reference image quality assessment (FR-IQA) models to assign pseudo-binary labels of each pair indicating which image has higher quality as the supervisory signal. We then train a convolutional neural network (CNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary labels. Since there exists domain shift between the synthetically- and authentically-distorted images, an unsupervised domain adaptation (UDA) module is introduced to alleviate this issue. Extensive experiments demonstrate the effectiveness of our proposed $opinion$-$free$ BIQA model, yielding state-of-the-art performance in terms of correlation with human opinion scores, as well as gMAD competition. Codes will be made publicly available upon acceptance.

Boyang Wan, Yuming Fang, Xue Xia et al.

Anomaly detection in surveillance videos is a challenging task due to the diversity of anomalous video content and duration. In this paper, we consider video anomaly detection as a regression problem with respect to anomaly scores of video clips under weak supervision. Hence, we propose an anomaly detection framework, called Anomaly Regression Net (AR-Net), which only requires video-level labels in training stage. Further, to learn discriminative features for anomaly detection, we design a dynamic multiple-instance learning loss and a center loss for the proposed AR-Net. The former is used to enlarge the inter-class distance between anomalous and normal instances, while the latter is proposed to reduce the intra-class distance of normal instances. Comprehensive experiments are performed on a challenging benchmark: ShanghaiTech. Our method yields a new state-of-the-art result for video anomaly detection on ShanghaiTech dataset

Jingwen Hou, Sheng Yang, Weisi Lin et al.

As it is said by Van Gogh, great things are done by a series of small things brought together. Aesthetic experience arises from the aggregation of underlying visual components. However, most existing deep image aesthetic assessment (IAA) methods over-simplify the IAA process by failing to model image aesthetics with clearly-defined visual components as building blocks. As a result, the connection between resulting aesthetic predictions and underlying visual components is mostly invisible and hard to be explicitly controlled, which limits the model in both performance and interpretability. This work aims to model image aesthetics from the level of visual components. Specifically, object-level regions detected by a generic object detector are defined as visual components, namely object-level visual components (OVCs). Then generic features representing OVCs are aggregated for the aesthetic prediction based upon proposed object-level and graph attention mechanisms, which dynamically determines the importance of individual OVCs and relevance between OVC pairs, respectively. Experimental results confirm the superiority of our framework over previous relevant methods in terms of SRCC and PLCC on the aesthetic rating distribution prediction. Besides, quantitative analysis is done towards model interpretation by observing how OVCs contribute to aesthetic predictions, whose results are found to be supported by psychology on aesthetics and photography rules. To the best of our knowledge, this is the first attempt at the interpretation of a deep IAA model.

Wenying Wen, Rongxin Tu, Yushu Zhang et al.

High-efficiency video coding (HEVC) encryption has been proposed to encrypt syntax elements for the purpose of video encryption. To achieve high video security, to the best of our knowledge, almost all of the existing HEVC encryption algorithms mainly encrypt the whole video, such that the user without permissions cannot obtain any viewable information. However, these encryption algorithms cannot meet the needs of customers who need part of the information but not the full information in the video. In many cases, such as professional paid videos or video meetings, users would like to observe some visible information in the encrypted video of the original video to satisfy their requirements in daily life. Aiming at this demand, this paper proposes a multi-level encryption scheme that is composed of lightweight encryption, medium encryption and heavyweight encryption, where each encryption level can obtain a different amount of visual information. It is found that both encrypting the luma intraprediction model (IPM) and scrambling the syntax element of the DCT coefficient sign can achieve the performance of a distorted video in which there is still residual visual information, while encrypting both of them can implement the intensity of encryption and one cannot gain any visual information. The experimental results meet our expectations appropriately, indicating that there is a different amount of visual information in each encryption level. Meanwhile, users can flexibly choose the encryption level according to their various requirements.

Chenglizhao Chen, Jia Song, Chong Peng et al.

Previous video salient object detection (VSOD) approaches have mainly focused on designing fancy networks to achieve their performance improvements. However, with the slow-down in development of deep learning techniques recently, it may become more and more difficult to anticipate another breakthrough via fancy networks solely. To this end, this paper proposes a universal learning scheme to get a further 3\% performance improvement for all state-of-the-art (SOTA) methods. The major highlight of our method is that we resort the "motion quality"---a brand new concept, to select a sub-group of video frames from the original testing set to construct a new training set. The selected frames in this new training set should all contain high-quality motions, in which the salient objects will have large probability to be successfully detected by the "target SOTA method"---the one we want to improve. Consequently, we can achieve a significant performance improvement by using this new training set to start a new round of network training. During this new round training, the VSOD results of the target SOTA method will be applied as the pseudo training objectives. Our novel learning scheme is simple yet effective, and its semi-supervised methodology may have large potential to inspire the VSOD community in the future.

Xiangjie Sui, Kede Ma, Yiru Yao et al.

Omnidirectional images (also referred to as static 360° panoramas) impose viewing conditions much different from those of regular 2D images. How do humans perceive image distortions in immersive virtual reality (VR) environments is an important problem which receives less attention. We argue that, apart from the distorted panorama itself, two types of VR viewing conditions are crucial in determining the viewing behaviors of users and the perceived quality of the panorama: the starting point and the exploration time. We first carry out a psychophysical experiment to investigate the interplay among the VR viewing conditions, the user viewing behaviors, and the perceived quality of 360° images. Then, we provide a thorough analysis of the collected human data, leading to several interesting findings. Moreover, we propose a computational framework for objective quality assessment of 360° images, embodying viewing conditions and behaviors in a delightful way. Specifically, we first transform an omnidirectional image to several video representations using different user viewing behaviors under different viewing conditions. We then leverage advanced 2D full-reference video quality models to compute the perceived quality. We construct a set of specific quality measures within the proposed framework, and demonstrate their promises on three VR quality databases.

Wenhan Yang, Robby T. Tan, Shiqi Wang et al.

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future directions.

Nevrez Imamoglu, Guanqun Ding, Yuming Fang et al.

Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us to obtain redundant spectral information of the observed scenes from the reflected light source from objects. A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved. In this work, we proposed a salient object detection model on hyperspectral images by applying manifold ranking (MR) on self-supervised Convolutional Neural Network (CNN) features (high-level features) from unsupervised image segmentation task. Self-supervision of CNN continues until clustering loss or saliency maps converges to a defined error between each iteration. Finally, saliency estimations is done as the saliency map at last iteration when the self-supervision procedure terminates with convergence. Experimental evaluations demonstrated that proposed saliency detection algorithm on hyperspectral images is outperforming state-of-the-arts hyperspectral saliency models including the original MR based saliency model.

Yuming Fang, Guanqun Ding, Yuan Yuan et al.

To obtain effective pedestrian detection results in surveillance video, there have been many methods proposed to handle the problems from severe occlusion, pose variation, clutter background, \emph{etc}. Besides detection accuracy, a robust surveillance video system should be stable to video quality degradation by network transmission, environment variation, etc. In this study, we conduct the research on the robustness of pedestrian detection algorithms to video quality degradation. The main contribution of this work includes the following three aspects. First, a large-scale Distorted Surveillance Video Data Set (DSurVD) is constructed from high-quality video sequences and their corresponding distorted versions. Second, we design a method to evaluate detection stability and a robustness measure called Robustness Quadrangle, which can be adopted to visualize detection accuracy of pedestrian detection algorithms on high-quality video sequences and stability with video quality degradation. Third, the robustness of seven existing pedestrian detection algorithms is evaluated by the built DSurVD. Experimental results show that the robustness can be further improved for existing pedestrian detection algorithms. Additionally, we provide much in-depth discussion on how different distortion types influence the performance of pedestrian detection algorithms, which is important to design effective pedestrian detection algorithms for surveillance. The DSurVD data set can be download from BaiduYunDisk, https://pan.baidu.com/s/1I9Kqj8rmubOYu7bkBfkUpA, Password: lqmc

Guanqun Ding, Yuming Fang

Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks. First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences. Then, we design a 3D deconvolutional network (Deconv3DNet) to combine the spatiotemporal features to predict the final saliency map for video sequences. Experimental results show that the proposed saliency detection model performs better in video saliency prediction compared with the state-of-the-art video saliency detection methods.

Nevrez Imamoglu, Yu Oishi, Xiaoqiang Zhang et al.

Many works have been done on salient object detection using supervised or unsupervised approaches on colour images. Recently, a few studies demonstrated that efficient salient object detection can also be implemented by using spectral features in visible spectrum of hyperspectral images from natural scenes. However, these models on hyperspectral salient object detection were tested with a very few number of data selected from various online public dataset, which are not specifically created for object detection purposes. Therefore, here, we aim to contribute to the field by releasing a hyperspectral salient object detection dataset with a collection of 60 hyperspectral images with their respective ground-truth binary images and representative rendered colour images (sRGB). We took several aspects in consideration during the data collection such as variation in object size, number of objects, foreground-background contrast, object position on the image, and etc. Then, we prepared ground truth binary images for each hyperspectral data, where salient objects are labelled on the images. Finally, we did performance evaluation using Area Under Curve (AUC) metric on some existing hyperspectral saliency detection models in literature.

Nevrez Imamoglu, Chi Zhang, Wataru Shimoda et al.

As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the object class is in the network knowledge or not. In this paper, we propose a top-down saliency model using CNN, a weakly supervised CNN model trained for 1000 object labelling task from RGB images. The model detects attentive regions based on their objectness scores predicted by selected features from CNNs. To estimate the salient objects effectively, we combine both forward and backward features, while demonstrating that partially-guided backpropagation will provide sufficient information for selecting the features from forward run of CNN model. Finally, these top-down cues are enhanced with a state-of-the-art bottom-up model as complementing the overall saliency. As the proposed model is an effective integration of forward and backward cues through objectness without any supervision or regression to ground truth data, it gives promising results compared to state-of-the-art models in two different datasets.