Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain

RAW to sRGB mapping, which aims to convert RAW images from smartphones into RGB form equivalent to that of Digital Single-Lens Reflex (DSLR) cameras, has become an important area of research. However, current methods often ignore the difference between cell phone RAW images and DSLR camera RGB images, a difference that goes beyond the color matrix and extends to spatial structure due to resolution variations. Recent methods directly rebuild color mapping and spatial structure via shared deep representation, limiting optimal performance. Inspired by Image Signal Processing (ISP) pipeline, which distinguishes image restoration and enhancement, we present a novel Neural ISP framework, named FourierISP. This approach breaks the image down into style and structure within the frequency domain, allowing for independent optimization. FourierISP is comprised of three subnetworks: Phase Enhance Subnet for structural refinement, Amplitude Refine Subnet for color learning, and Color Adaptation Subnet for blending them in a smooth manner. This approach sharpens both color and structure, and extensive evaluations across varied datasets confirm that our approach realizes state-of-the-art results. Code will be available at ~\url{https://github.com/alexhe101/FourierISP}.

ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration

Image restoration aims to reconstruct degraded images, e.g., denoising or deblurring. Existing works focus on designing task-specific methods and there are inadequate attempts at universal methods. However, simply unifying multiple tasks into one universal architecture suffers from uncontrollable and undesired predictions. To address those issues, we explore prompt learning in universal architectures for image restoration tasks. In this paper, we present Degradation-aware Visual Prompts, which encode various types of image degradation, e.g., noise and blur, into unified visual prompts. These degradation-aware prompts provide control over image processing and allow weighted combinations for customized image restoration. We then leverage degradation-aware visual prompts to establish a controllable and universal model for image restoration, called ProRes, which is applicable to an extensive range of image restoration tasks. ProRes leverages the vanilla Vision Transformer (ViT) without any task-specific designs. Furthermore, the pre-trained ProRes can easily adapt to new tasks through efficient prompt tuning with only a few images. Without bells and whistles, ProRes achieves competitive performance compared to task-specific methods and experiments can demonstrate its ability for controllable restoration and adaptation for new tasks. The code and models will be released in \url{https://github.com/leonmakise/ProRes}.

Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer

Wind power is attracting increasing attention around the world due to its renewable, pollution-free, and other advantages. However, safely and stably integrating the high permeability intermittent power energy into electric power systems remains challenging. Accurate wind power forecasting (WPF) can effectively reduce power fluctuations in power system operations. Existing methods are mainly designed for short-term predictions and lack effective spatial-temporal feature augmentation. In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems. Specifically, we construct an hourglass-shaped encoder-decoder framework with skip-connections to jointly model representations aggregated in hierarchical temporal scales, which benefits long-term forecasting. Based on this framework, we capture the inter-scale long-range temporal dependencies and global spatial correlations with two parallel Transformer skeletons and strengthen the intra-scale connections with downsampling and upsampling operations. Moreover, the complementary information from spatial and temporal features is fused and propagated in each other via Contextual Fusion Blocks (CFBs) to promote the prediction further. Extensive experimental results on two large-scale real-world datasets demonstrate the superior performance of our HSTTN over existing solutions.

OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation

Open-world instance segmentation has recently gained significant popularitydue to its importance in many real-world applications, such as autonomous driving, robot perception, and remote sensing. However, previous methods have either produced unsatisfactory results or relied on complex systems and paradigms. We wonder if there is a simple way to obtain state-of-the-art results. Fortunately, we have identified two observations that help us achieve the best of both worlds: 1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and 2) learning localization cues is sufficient for open world instance segmentation. Based on these observations, we propose a simple query-based method named OpenInst for open world instance segmentation. OpenInst leverages advanced query-based methods like QueryInst and focuses on learning localization cues. Notably, OpenInst is an extremely simple and straightforward framework without any auxiliary modules or post-processing, yet achieves state-of-the-art results on multiple benchmarks. Specifically, in the COCO$\to$UVO scenario, OpenInst achieves a mask AR of 53.3, outperforming the previous best methods by 2.0 AR with a simpler structure. We hope that OpenInst can serve as a solid baselines for future research in this area.

MM-SFENet: Multi-scale Multi-task Localization and Classification of Bladder Cancer in MRI with Spatial Feature Encoder Network

Background and Objective: Bladder cancer is a common malignant urinary carcinoma, with muscle-invasive and non-muscle-invasive as its two major subtypes. This paper aims to achieve automated bladder cancer invasiveness localization and classification based on MRI. Method: Different from previous efforts that segment bladder wall and tumor, we propose a novel end-to-end multi-scale multi-task spatial feature encoder network (MM-SFENet) for locating and classifying bladder cancer, according to the classification criteria of the spatial relationship between the tumor and bladder wall. First, we built a backbone with residual blocks to distinguish bladder wall and tumor; then, a spatial feature encoder is designed to encode the multi-level features of the backbone to learn the criteria. Results: We substitute Smooth-L1 Loss with IoU Loss for multi-task learning, to improve the accuracy of the classification task. By testing a total of 1287 MRIs collected from 98 patients at the hospital, the mAP and IoU are used as the evaluation metrics. The experimental result could reach 93.34\% and 83.16\% on test set. Conclusions: The experimental result demonstrates the effectiveness of the proposed MM-SFENet on the localization and classification of bladder cancer. It may provide an effective supplementary diagnosis method for bladder cancer staging.

BB-GCN: A Bi-modal Bridged Graph Convolutional Network for Multi-label Chest X-Ray Recognition

Multi-label chest X-ray (CXR) recognition involves simultaneously diagnosing and identifying multiple labels for different pathologies. Since pathological labels have rich information about their relationship to each other, modeling the co-occurrence dependencies between pathological labels is essential to improve recognition performance. However, previous methods rely on state variable coding and attention mechanisms-oriented to model local label information, and lack learning of global co-occurrence relationships between labels. Furthermore, these methods roughly integrate image features and label embedding, ignoring the alignment and compactness problems in cross-modal vector fusion.To solve these problems, a Bi-modal Bridged Graph Convolutional Network (BB-GCN) model is proposed. This model mainly consists of a backbone module, a pathology Label Co-occurrence relationship Embedding (LCE) module, and a Transformer Bridge Graph (TBG) module. Specifically, the backbone module obtains image visual feature representation. The LCE module utilizes a graph to model the global co-occurrence relationship between multiple labels and employs graph convolutional networks for learning inference. The TBG module bridges the cross-modal vectors more compactly and efficiently through the GroupSum method.We have evaluated the effectiveness of the proposed BB-GCN in two large-scale CXR datasets (ChestX-Ray14 and CheXpert). Our model achieved state-of-the-art performance: the mean AUC scores for the 14 pathologies were 0.835 and 0.813, respectively.The proposed LCE and TBG modules can jointly effectively improve the recognition performance of BB-GCN. Our model also achieves satisfactory results in multi-label chest X-ray recognition and exhibits highly competitive generalization performance.

ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer

In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contains two core designs especially for raw images whose primitive attribute is single-channel. The first design is a Bi-directional Fusion Projection (BFP) module, where we consider both the color characteristics of raw images and spatial structure of single-channel. The second one is that we propose a Locally Multiplicative Self-Attention (L-MSA) scheme to effectively deliver information from the local space to relevant parts. ELMformer can efficiently reduce the computational consumption and perform well on raw image restoration tasks. Enhanced by these two core designs, ELMformer achieves the highest performance and keeps the lowest FLOPs on raw denoising and raw deblurring benchmarks compared with state-of-the-arts. Extensive experiments demonstrate the superiority and generalization ability of ELMformer. On SIDD benchmark, our method has even better denoising performance than ISP-based methods which need huge amount of additional sRGB training images. The codes are release at https://github.com/leonmakise/ELMformer.

Towards Real-Time Visual Tracking with Graded Color-names Features

MeanShift algorithm has been widely used in tracking tasks because of its simplicity and efficiency. However, the traditional MeanShift algorithm needs to label the initial region of the target, which reduces the applicability of the algorithm. Furthermore, it is only applicable to the scene with a large overlap rate between the target area and the candidate area. Therefore, when the target speed is fast, the target scale change, shape deformation or the target occlusion occurs, the tracking performance will be deteriorated. In this paper, we address the challenges above-mentioned by developing a tracking method that combines the background models and the graded features of color-names under the MeanShift framework. This method significantly improve performance in the above scenarios. In addition, it facilitates the balance between detection accuracy and detection speed. Experimental results demonstrate the validation of the proposed method.

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the intermediate target domain to perform the adaptation from daytime to nighttime, may fail to cope with the inherent difference between datasets caused by the camera equipment and the urban style. Faced with these two types of domain shifts, i.e., the illumination and the inherent difference of the datasets, we propose a novel domain adaptation framework via cross-domain correlation distillation, called CCDistill. The invariance of illumination or inherent difference between two images is fully explored so as to make up for the lack of labels for nighttime images. Specifically, we extract the content and style knowledge contained in features, calculate the degree of inherent or illumination difference between two images. The domain adaptation is achieved using the invariance of the same kind of difference. Extensive experiments on Dark Zurich and ACDC demonstrate that CCDistill achieves the state-of-the-art performance for nighttime semantic segmentation. Notably, our method is a one-stage domain adaptation network which can avoid affecting the inference time. Our implementation is available at https://github.com/ghuan99/CCDistill.

Learning Quality-aware Representation for Multi-person Pose Regression

Off-the-shelf single-stage multi-person pose regression methods generally leverage the instance score (i.e., confidence of the instance localization) to indicate the pose quality for selecting the pose candidates. We consider that there are two gaps involved in existing paradigm:~1) The instance score is not well interrelated with the pose regression quality.~2) The instance feature representation, which is used for predicting the instance score, does not explicitly encode the structural pose information to predict the reasonable score that represents pose regression quality. To address the aforementioned issues, we propose to learn the pose regression quality-aware representation. Concretely, for the first gap, instead of using the previous instance confidence label (e.g., discrete {1,0} or Gaussian representation) to denote the position and confidence for person instance, we firstly introduce the Consistent Instance Representation (CIR) that unifies the pose regression quality score of instance and the confidence of background into a pixel-wise score map to calibrates the inconsistency between instance score and pose regression quality. To fill the second gap, we further present the Query Encoding Module (QEM) including the Keypoint Query Encoding (KQE) to encode the positional and semantic information for each keypoint and the Pose Query Encoding (PQE) which explicitly encodes the predicted structural pose information to better fit the Consistent Instance Representation (CIR). By using the proposed components, we significantly alleviate the above gaps. Our method outperforms previous single-stage regression-based even bottom-up methods and achieves the state-of-the-art result of 71.7 AP on MS COCO test-dev set.