arXiv subjects

Jinyuan Liu

Publications and source records attributed to Jinyuan Liu.

86 records · Page 5Linked to original sources

arXiv2023

Multi-Spectral Image Stitching via Spatial Graph Reasoning

Multi-spectral image stitching leverages the complementarity between infrared and visible images to generate a robust and reliable wide field-of-view (FOV) scene. The primary challenge of this task is to explore the relations between multi-spectral images for aligning and integrating multi-view scenes. Capitalizing on the strengths of Graph Convolutional Networks (GCNs) in modeling feature relationships, we propose a spatial graph reasoning based multi-spectral image stitching method that effectively distills the deformation and integration of multi-spectral images across different viewpoints. To accomplish this, we embed multi-scale complementary features from the same view position into a set of nodes. The correspondence across different views is learned through powerful dense feature embeddings, where both inter- and intra-correlations are developed to exploit cross-view matching and enhance inner feature disparity. By introducing long-range coherence along spatial and channel dimensions, the complementarity of pixel relations and channel interdependencies aids in the reconstruction of aligned multi-view features, generating informative and reliable wide FOV scenes. Moreover, we release a challenging dataset named ChaMS, comprising both real-world and synthetic sets with significant parallax, providing a new option for comprehensive evaluation. Extensive experiments demonstrate that our method surpasses the state-of-the-arts.

cs.CV↗

arXiv2023

Bilevel Fast Scene Adaptation for Low-Light Image Enhancement

Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before. The main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. To remedy this, we first explore relationships between diverse low-light scenes based on statistical analysis, i.e., the network parameters of the encoder trained in different data distributions are close. We introduce the bilevel paradigm to model the above latent correspondence from the perspective of hyperparameter optimization. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i.e., freezing the encoder in the adaptation and testing phases). Further, we define a reinforced bilevel learning framework to provide a meta-initialization for scene-specific decoder to further ameliorate visual quality. Moreover, to improve the practicability, we establish a Retinex-induced architecture with adaptive denoising and apply our built learning framework to acquire its parameters by using two training losses including supervised and unsupervised forms. Extensive experimental evaluations on multiple datasets verify our adaptability and competitive performance against existing state-of-the-art works. The code and datasets will be available at https://github.com/vis-opt-group/BL.

cs.CV↗

arXiv2023

MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

3D object detection plays a crucial role in numerous intelligent vision systems. Detection in the open world inevitably encounters various adverse scenes, such as dense fog, heavy rain, and low light conditions. Although existing efforts primarily focus on diversifying network architecture or training schemes, resulting in significant progress in 3D object detection, most of these learnable modules fail in adverse scenes, thereby hindering detection performance. To address this issue, this paper proposes a monocular 3D detection model designed to perceive twin depth in adverse scenes, termed MonoTDP, which effectively mitigates the degradation of detection performance in various harsh environments. Specifically, we first introduce an adaptive learning strategy to aid the model in handling uncontrollable weather conditions, significantly resisting degradation caused by various degrading factors. Then, to address the depth/content loss in adverse regions, we propose a novel twin depth perception module that simultaneously estimates scene and object depth, enabling the integration of scene-level features and object-level features. Additionally, we assemble a new adverse 3D object detection dataset encompassing a wide range of challenging scenes, including rainy, foggy, and low light weather conditions, with each type of scene containing 7,481 images. Experimental results demonstrate that our proposed method outperforms current state-of-the-art approaches by an average of 3.12% in terms of AP_R40 for car category across various adverse environments.

cs.CV↗

arXiv2023

A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion

Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore, designing proper fusion architectures often requires huge engineering labor. It also lacks mechanisms to improve the flexibility and generalization ability of current fusion approaches. To mitigate these issues, we establish a Task-guided, Implicit-searched and Meta-initialized (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we first propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency. In addition, a pretext meta initialization technique is introduced to leverage divergence fusion data to support fast adaptation for different kinds of image fusion tasks. Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e.g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM. The source code will be available at https://github.com/LiuZhu-CV/TIMFusion.

cs.CV↗

arXiv2023

An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection

This research focuses on the discovery and localization of hidden objects in the wild and serves unmanned systems. Through empirical analysis, infrared and visible image fusion (IVIF) enables hard-to-find objects apparent, whereas multimodal salient object detection (SOD) accurately delineates the precise spatial location of objects within the picture. Their common characteristic of seeking complementary cues from different source images motivates us to explore the collaborative relationship between Fusion and Salient object detection tasks on infrared and visible images via an Interactively Reinforced multi-task paradigm for the first time, termed IRFS. To the seamless bridge of multimodal image fusion and SOD tasks, we specifically develop a Feature Screening-based Fusion subnetwork (FSFNet) to screen out interfering features from source images, thereby preserving saliency-related features. After generating the fused image through FSFNet, it is then fed into the subsequent Fusion-Guided Cross-Complementary SOD subnetwork (FC$^2$Net) as the third modality to drive the precise prediction of the saliency map by leveraging the complementary information derived from the fused image. In addition, we develop an interactive loop learning strategy to achieve the mutual reinforcement of IVIF and SOD tasks with a shorter training period and fewer network parameters. Comprehensive experiment results demonstrate that the seamless bridge of IVIF and SOD mutually enhances their performance, and highlights their superiority.

cs.CV↗

arXiv2023

Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and neglecting others, seldom investigating their underlying connections for joint promotion. To overcome these limitations, we establish the hierarchical dual tasks-driven deep model to bridge these tasks. Concretely, we firstly construct an image fusion module to fuse complementary characteristics and cascade dual task-related modules, including a discriminator for visual effects and a semantic network for feature measurement. We provide a bi-level perspective to formulate image fusion and follow-up downstream tasks. To incorporate distinct task-related responses for image fusion, we consider image fusion as a primary goal and dual modules as learnable constraints. Furthermore, we develop an efficient first-order approximation to compute corresponding gradients and present dynamic weighted aggregation to balance the gradients for fusion learning. Extensive experiments demonstrate the superiority of our method, which not only produces visually pleasant fused results but also realizes significant promotion for detection and segmentation than the state-of-the-art approaches.

cs.CV↗

arXiv2023

Energy Efficiency of Rate-Splitting Multiple Access for Multibeam Satellite System

Energy efficiency (EE) problem has become an important and major issue in satellite communications. In this paper, we study the beamforming design strategy to maximize the EE of rate-splitting multiple access (RSMA) for the multibeam satellite communications by considering imperfect channel state information at the transmitter (CSIT). We propose an expectation-based robust beamforming algorithm against the imperfect CSIT scenario. By combining the successive convex approximation (SCA) with the penalty function transformation, the nonconvex EE maximization problem can be solved in an iterative manner. The simulation results demonstrate the effectiveness and superiority of RSMA over traditional space division multiple access (SDMA). Moreover, our proposed beamforming algorithm can achieve better EE performance than the conventional beamforming algorithm.

cs.IT↗

arXiv2022

Breaking Free from Fusion Rule: A Fully Semantic-driven Infrared and Visible Image Fusion

Infrared and visible image fusion plays a vital role in the field of computer vision. Previous approaches make efforts to design various fusion rules in the loss functions. However, these experimental designed fusion rules make the methods more and more complex. Besides, most of them only focus on boosting the visual effects, thus showing unsatisfactory performance for the follow-up high-level vision tasks. To address these challenges, in this letter, we develop a semantic-level fusion network to sufficiently utilize the semantic guidance, emancipating the experimental designed fusion rules. In addition, to achieve a better semantic understanding of the feature fusion process, a fusion block based on the transformer is presented in a multi-scale manner. Moreover, we devise a regularization loss function, together with a training strategy, to fully use semantic guidance from the high-level vision tasks. Compared with state-of-the-art methods, our method does not depend on the hand-crafted fusion loss function. Still, it achieves superior performance on visual quality along with the follow-up high-level vision tasks.

cs.CV↗

arXiv2022

Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration

Recent learning-based image fusion methods have marked numerous progress in pre-registered multi-modality data, but suffered serious ghosts dealing with misaligned multi-modality data, due to the spatial deformation and the difficulty narrowing cross-modality discrepancy. To overcome the obstacles, in this paper, we present a robust cross-modality generation-registration paradigm for unsupervised misaligned infrared and visible image fusion (IVIF). Specifically, we propose a Cross-modality Perceptual Style Transfer Network (CPSTN) to generate a pseudo infrared image taking a visible image as input. Benefiting from the favorable geometry preservation ability of the CPSTN, the generated pseudo infrared image embraces a sharp structure, which is more conducive to transforming cross-modality image alignment into mono-modality registration coupled with the structure-sensitive of the infrared image. In this case, we introduce a Multi-level Refinement Registration Network (MRRN) to predict the displacement vector field between distorted and pseudo infrared images and reconstruct registered infrared image under the mono-modality setting. Moreover, to better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM) to adaptively select more meaningful features for fusion in the Dual-path Interaction Fusion Network (DIFN). Extensive experimental results suggest that the proposed method performs superior capability on misaligned cross-modality image fusion.

cs.CV↗

arXiv2022

On Semiparametric Efficiency of an Emerging Class of Regression Models for Between-subject Attributes

The semiparametric regression models have attracted increasing attention owing to their robustness compared to their parametric counterparts. This paper discusses the efficiency bound for functional response models (FRM), an emerging class of semiparametric regression that serves as a timely solution for research questions involving pairwise observations. This new paradigm is especially appealing to reduce astronomical data dimensions for those arising from wearable devices and high-throughput technology, such as microbiome Beta-diversity, viral genetic linkage, single-cell RNA sequencing, etc. Despite the growing applications, the efficiency of their estimators has not been investigated carefully due to the extreme difficulty to address the inherent correlations among pairs. Leveraging the Hilbert-space-based semiparametric efficiency theory for classical within-subject attributes, this manuscript extends such asymptotic efficiency into the broader regression involving between-subject attributes and pinpoints the most efficient estimator, which leads to a sensitive signal-detection in practice. With pairwise outcomes burgeoning immensely as effective dimension-reduction summaries, the established theory will not only fill the critical gap in identifying the most efficient semiparametric estimator but also propel wide-ranging implementations of this new paradigm for between-subject attributes.

stat.ME↗

arXiv2022

Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection

This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network. The fusion network with one generator and dual discriminators seeks commons while learning from differences, which preserves structural information of targets from the infrared and textural details from the visible. Furthermore, we build a synchronized imaging system with calibrated infrared and optical sensors, and collect currently the most comprehensive benchmark covering a wide range of scenarios. Extensive experiments on several public datasets and our benchmark demonstrate that our method outputs not only visually appealing fusion but also higher detection mAP than the state-of-the-art approaches.

cs.CV↗

arXiv2021

Solid-Fluid Interaction with Surface-Tension-Dominant Contact

We propose a novel three-way coupling method to model the contact interaction between solid and fluid driven by strong surface tension. At the heart of our physical model is a thin liquid membrane that simultaneously couples to both the liquid volume and the rigid objects, facilitating accurate momentum transfer, collision processing, and surface tension calculation. This model is implemented numerically under a hybrid Eulerian-Lagrangian framework where the membrane is modelled as a simplicial mesh and the liquid volume is simulated on a background Cartesian grid. We devise a monolithic solver to solve the interactions among the three systems of liquid, solid, and membrane. We demonstrate the efficacy of our method through an array of rigid-fluid contact simulations dominated by strong surface tension, which enables the faithful modeling of a host of new surface-tension-dominant phenomena including: objects with higher density than water can keep afloat on top of it; 'Cheerios effect' about floating objects that do not normally float attract one another; surface tension weakening effect caused by surface-active constituents.

physics.flu-dyn↗

arXiv2021

A new tool for two-dimensional field-reversed configuration equilibrium study

A new tool (GSEQ-FRC) for solving two-dimensional (2D) equilibrium of field-reversed configuration (FRC) based on fixed boundary and free boundary conditions with external coils included is developed. Benefiting from the two-parameter modified rigid rotor (MRR) radial equilibrium model and the numerical approaches presented by [Ma et al, Nucl. Fusion, 61, 036046, 2021], GSEQ-FRC are used to study the equilibrium properties of FRC quantitatively and will be used for fast FRC equilibrium reconstruction. In GSEQ-FRC, the FRC equilibrium can be conveniently determined by two parameters, i.e., the ratio between thermal pressure and magnetic pressure at the seperatrix $β_s$, and the normalized scrape of layer (SOL) width $δ_s$. Examples with fixed and free boundary conditions are given to demonstrate the capability of GSEQ-FRC in the equilibrium calculations. This new tool is used to quantitatively study the factors affecting the shape of the FRC separatrix, revealing how the FRC changes from racetrack-like to ellipse-like.

physics.plasm-ph↗

arXiv2020

Two-parameter Radial Equilibrium Models for Field-Reversed Configurations

A new equilibrium pressure profile extending the Rigid-Rotor (RR) model with a simple unified expression $P=P(ψ;β_{s},α, σ)$ for both inside and outside the separatrix is proposed, in which the radial normalized field-reversed configuration (FRC) equilibrium profiles for pressure, magnetic field, and current can be determined by only two dimensionless parameters $β_s\equiv P_s/2μ_0B_e^2$ and $δ_s\equiv L_{ps}/R_s$, where $P_s$ is the thermal pressure at the separatrix, $B_e$ is the external magnetic field strength, $L_{ps}$ is the pressure profile scale length at the separatrix, and $R_s$ is the separatrix radius. This modified rigid rotor (MRR) model has sufficient flexibility to accommodate the narrow scrape of layer (SOL) width and hollow current density profiles, and can be used to fit experimental measurements satisfactorily. Detailed one-dimensional (1D) characteristics of the new MRR model are investigated analytically and numerically, and the results are also confirmed in two-dimensional (2D) numerical equilibrium solutions.

physics.plasm-ph↗