arXiv subjects

Jinyuan Liu

Publications and source records attributed to Jinyuan Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Bridging Human Evaluation to Infrared and Visible Image Fusion

Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception. Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences. This challenge is further exacerbated by the ill-posed nature of IVIF, which severely limits its effectiveness in human perceptual environments such as security surveillance and driver assistance systems. To address these limitations, we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion. To address the lack of human-centric evaluation metrics and data, we introduce the first large-scale human feedback dataset for IVIF, containing multidimensional subjective scores and artifact annotations, and enriched by a fine-tuned large language model with expert review. Based on this dataset, we design a domain-specific reward function and train a reward model to quantify perceptual quality. Guided by this reward, we fine-tune the fusion network through Group Relative Policy Optimization, achieving state-of-the-art performance that better aligns fused images with human aesthetics. Code is available at https://github.com/ALKA-Wind/EVAFusion.

cs.CV↗

arXiv2026

RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels

Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar.

cs.CV↗

arXiv2026

HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution

Infrared video has been of great interest in visual tasks under challenging environments, but often suffers from severe atmospheric turbulence and compression degradation. Existing video super-resolution (VSR) methods either neglect the inherent modality gap between infrared and visible images or fail to restore turbulence-induced distortions. Directly cascading turbulence mitigation (TM) algorithms with VSR methods leads to error propagation and accumulation due to the decoupled modeling of degradation between turbulence and resolution. We introduce HATIR, a Heat-Aware Diffusion for Turbulent InfraRed Video Super-Resolution, which injects heat-aware deformation priors into the diffusion sampling path to jointly model the inverse process of turbulent degradation and structural detail loss. Specifically, HATIR constructs a Phasor-Guided Flow Estimator, rooted in the physical principle that thermally active regions exhibit consistent phasor responses over time, enabling reliable turbulence-aware flow to guide the reverse diffusion process. To ensure the fidelity of structural recovery under nonuniform distortions, a Turbulence-Aware Decoder is proposed to selectively suppress unstable temporal cues and enhance edge-aware feature aggregation via turbulence gating and structure-aware attention. We built FLIR-IVSR, the first dataset for turbulent infrared VSR, comprising paired LR-HR sequences from a FLIR T1050sc camera (1024 X 768) spanning 640 diverse scenes with varying camera and object motion conditions. This encourages future research in infrared VSR. Project page: https://github.com/JZ0606/HATIR

cs.CV↗

arXiv2025

LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration

Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in viewpoint, and dynamic structures, especially in long-horizon navigation. However, current UAV vision-and-language navigation(VLN) methods struggle to model long-horizon spatiotemporal context in complex environments, resulting in inaccurate semantic alignment and unstable path planning. To this end, we propose LongFly, a spatiotemporal context modeling framework for long-horizon UAV VLN. LongFly proposes a history-aware spatiotemporal modeling strategy that transforms fragmented and redundant historical data into structured, compact, and expressive representations. First, we propose the slot-based historical image compression module, which dynamically distills multi-view historical observations into fixed-length contextual representations. Then, the spatiotemporal trajectory encoding module is introduced to capture the temporal dynamics and spatial structure of UAV trajectories. Finally, to integrate existing spatiotemporal context with current observations, we design the prompt-guided multimodal integration module to support time-based reasoning and robust waypoint prediction. Experimental results demonstrate that LongFly outperforms state-of-the-art UAV VLN baselines by 7.89\% in success rate and 6.33\% in success weighted by path length, consistently across both seen and unseen environments.

cs.CV↗

arXiv2025

FAS-RSMA: Can Fluid Antennas Elevate RSMA Performance?

As 6G networks demand massive connectivity and stronger interference control, rate-splitting multiple access (RSMA) is attractive because it superposes a common stream and user-private streams and remains effective under imperfect CSIT and heterogeneous traffic. In practical multiuser deployments, two considerations arise: the common stream decoding constraint imposed by the weakest user, and residual inter-user interference can remain non-negligible, particularly in single-input single-output (SISO) broadcast settings and under an imperfect CSIT scenario. Motivated by prior advances of RSMA research, we investigate a complementary mechanism-fluid antenna systems (FAS), with dynamic port reconfiguration supplies adaptive spatial selectivity without altering the RSMA signaling structure. Can FAS help alleviate these considerations and enhance RSMA performance? We develop a tractable correlation-aware analytical framework based on block-correlation models, including constant block correlation (CBC) and variable block correlation (VBC), to capture realistic spatial dependence among ports. Closed-form expressions are derived for outage probability (OP) and average capacity (AC), revealing how port reconfiguration strengthens the weakest effective channel and improves SINR through higher channel gains and lower relative noise impact. Monte Carlo simulations verify the analysis and show that VBC matches simulations more tightly than CBC across all port configurations. Finally, FAS-RSMA provides clear gains over conventional antenna systems and NOMA, achieving lower OP and higher AC by combining RSMA interference management with FAS spatial diversity.

eess.SP↗

arXiv2025

Why Is the Double-Robust Estimator for Causal Inference Not Doubly Robust for Variance Estimation?

Doubly robust estimators (DRE) are widely used in causal inference because they yield consistent estimators of average causal effect when at least one of the nuisance models, the propensity for treatment (exposure) or the outcome regression, is correct. However, double robustness does not extend to variance estimation; the influence-function (IF)-based variance estimator is consistent only when both nuisance parameters are correct. This raises concerns about applying DRE in practice, where model misspecification is inevitable. The recent paper by Shook-Sa et al. (2025, Biometrics, 81(2), ujaf054) demonstrated through Monte Carlo simulations that the IF-based variance estimator is biased. However, the paper's findings are empirical. The key question remains: why does the variance estimator fail in double robustness, and under what conditions do alternatives succeed, such as the ones demonstrated in Shook-Sa et al. 2025. In this paper, we develop a formal theory to clarify the efficiency properties of DRE that underlie these empirical findings. We also introduce alternative strategies, including a mixture-based framework underlying the sample-splitting and crossfitting approaches, to achieve valid inference with misspecified nuisance parameters. Our considerations are illustrated with simulation and real study data.

stat.ME↗

arXiv2025

Depth-Supervised Fusion Network for Seamless-Free Image Stitching

Image stitching synthesizes images captured from multiple perspectives into a single image with a broader field of view. The significant variations in object depth often lead to large parallax, resulting in ghosting and misalignment in the stitched results. To address this, we propose a depth-consistency-constrained seamless-free image stitching method. First, to tackle the multi-view alignment difficulties caused by parallax, a multi-stage mechanism combined with global depth regularization constraints is developed to enhance the alignment accuracy of the same apparent target across different depth ranges. Second, during the multi-view image fusion process, an optimal stitching seam is determined through graph-based low-cost computation, and a soft-seam region is diffused to precisely locate transition areas, thereby effectively mitigating alignment errors induced by parallax and achieving natural and seamless stitching results. Furthermore, considering the computational overhead in the shift regression process, a reparameterization strategy is incorporated to optimize the structural design, significantly improving algorithm efficiency while maintaining optimal performance. Extensive experiments demonstrate the superior performance of the proposed method against the existing methods. Code is available at https://github.com/DLUT-YRH/DSFN.

cs.CV↗

arXiv2025

Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark

We engage in the relatively underexplored task named thermal infrared image enhancement. Existing infrared image enhancement methods primarily focus on tackling individual degradations, such as noise, contrast, and blurring, making it difficult to handle coupled degradations. Meanwhile, all-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness due to the significant differences in imaging models. In sight of this, we first revisit the imaging mechanism and introduce a Progressive Prompt Fusion Network (PPFN). Specifically, the PPFN initially establishes prompt pairs based on the thermal imaging process. For each type of degradation, we fuse the corresponding prompt pairs to modulate the model's features, providing adaptive guidance that enables the model to better address specific degradations under single or multiple conditions. In addition, a Selective Progressive Training (SPT) mechanism is introduced to gradually refine the model's handling of composite cases to align the enhancement process, which not only allows the model to remove camera noise and retain key structural details, but also enhancing the overall contrast of the thermal image. Furthermore, we introduce the most high-quality, multi-scenarios infrared benchmark covering a wide range of scenarios. Extensive experiments substantiate that our approach not only delivers promising visual results under specific degradation but also significantly improves performance on complex degradation scenes, achieving a notable 8.76\% improvement. Code is available at https://github.com/Zihang-Chen/HM-TIR.

cs.CV↗

arXiv2025

Efficient Rectified Flow for Image Fusion

Image fusion is a fundamental and important task in computer vision, aiming to combine complementary information from different modalities to fuse images. In recent years, diffusion models have made significant developments in the field of image fusion. However, diffusion models often require complex computations and redundant inference time, which reduces the applicability of these methods. To address this issue, we propose RFfusion, an efficient one-step diffusion model for image fusion based on Rectified Flow. We incorporate Rectified Flow into the image fusion task to straighten the sampling path in the diffusion model, achieving one-step sampling without the need for additional training, while still maintaining high-quality fusion results. Furthermore, we propose a task-specific variational autoencoder (VAE) architecture tailored for image fusion, where the fusion operation is embedded within the latent space to further reduce computational complexity. To address the inherent discrepancy between conventional reconstruction-oriented VAE objectives and the requirements of image fusion, we introduce a two-stage training strategy. This approach facilitates the effective learning and integration of complementary information from multi-modal source images, thereby enabling the model to retain fine-grained structural details while significantly enhancing inference efficiency. Extensive experiments demonstrate that our method outperforms other state-of-the-art methods in terms of both inference speed and fusion quality. Code is available at https://github.com/zirui0625/RFfusion.

cs.CV↗

arXiv2025

FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion

Reconstructing building floor plans from point cloud data is key for indoor navigation, BIM, and precise measurements. Traditional methods like geometric algorithms and Mask R-CNN-based deep learning often face issues with noise, limited generalization, and loss of geometric details. We propose FloorSAM, a framework that integrates point cloud density maps with the Segment Anything Model (SAM) for accurate floor plan reconstruction from LiDAR data. Using grid-based filtering, adaptive resolution projection, and image enhancement, we create robust top-down density maps. FloorSAM uses SAM's zero-shot learning for precise room segmentation, improving reconstruction across diverse layouts. Room masks are generated via adaptive prompt points and multistage filtering, followed by joint mask and point cloud analysis for contour extraction and regularization. This produces accurate floor plans and recovers room topological relationships. Tests on Giblayout and ISPRS datasets show better accuracy, recall, and robustness than traditional methods, especially in noisy and complex settings. Code and materials: github.com/Silentbarber/FloorSAM.

cs.CV↗

arXiv2025

A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering

Knowledge-based visual question answering (KB-VQA) requires a model to understand images and utilize external knowledge to provide accurate answers. Existing approaches often directly augment models with retrieved information from knowledge sources while ignoring substantial knowledge redundancy, which introduces noise into the answering process. To address this, we propose a training-free framework with knowledge focusing for KB-VQA, that mitigates the impact of noise by enhancing knowledge relevance and reducing redundancy. First, for knowledge retrieval, our framework concludes essential parts from the image-question pairs, creating low-noise queries that enhance the retrieval of highly relevant knowledge. Considering that redundancy still persists in the retrieved knowledge, we then prompt large models to identify and extract answer-beneficial segments from knowledge. In addition, we introduce a selective knowledge integration strategy, allowing the model to incorporate knowledge only when it lacks confidence in answering the question, thereby mitigating the influence of redundant information. Our framework enables the acquisition of accurate and critical knowledge, and extensive experiments demonstrate that it outperforms state-of-the-art methods.

cs.CV↗

arXiv2025

Turbulence in stratified rotating topographic wakes

Turbulence generation mechanisms in stratified, rotating flows past three-dimensional (3D) topography remain underexplored, particularly in submesoscale (SMS) regimes critical to geophysical applications. Using turbulence-resolving large-eddy simulations, we systematically dissect the interplay of stratification and rotation in governing the dynamics of wake turbulence. Our parametric study reveals that turbulent dissipation in the near wake is dominated by two distinct instabilities: (1) vertical shear-driven Kelvin-Helmholtz instability (KHI), amplified by oblique dislocation of Kármán vortices under strong stratification, and (2) centrifugal/inertial instability (CI), which peaks at intermediate rotation rates (Rossby number order unity, SMS regime) and relatively weaker stratification. Notably, strong rotation dampens vertical shear and weakens KHI-driven turbulence, while strong stratification imposes smaller vertical length scales that restrict CI-driven turbulence. By quantifying dissipation across a broad parameter space of stratification and rotation, predictive relationships between the environmental parameters and instability dominance is established. These findings highlight the regime dependence of instability mechanisms and may inform targeted observational campaigns and numerical models of oceanic and atmospheric wakes.

physics.flu-dyn↗

arXiv2025

Robust Beamforming Design for STAR-RIS Aided RSMA Network with Hardware Impairments

In this article, we investigate the robust beamforming design for a simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided downlink rate-splitting multiple access (RSMA) communication system, where both transceivers and STAR-RIS suffer from the impact of hardware impairments (HWI).A base station (BS) is deployed to transmit messages concurrently to multiple users, utilizing a STAR-RIS to improve communication quality and expand user coverage. We aim to maximize the achievable sum rate of the users while ensuring the constraints of transmit power, STAR-RIS coefficients, and the actual rate of the common stream for all users. To solve this challenging high-coupling and non-convexity problem, we adopt a fractional programming (FP)-based alternating optimization (AO) approach, where each sub-problem is addressed via successive convex approximation (SCA) and penalty function (PF) methods. Numerical results demonstrate that the proposed scheme outperforms other multiple access schemes and conventional passive RIS in terms of the achievable sum rate. Additionally, considering the HWI of the transceiver and STAR-RIS makes our algorithm more robust than when such considerations are not included.

eess.SP↗

arXiv2025

A Fast Method for Planning All Optimal Homotopic Configurations for Tethered Robots and Its Extended Applications

Tethered robots play a pivotal role in specialized environments such as disaster response and underground exploration, where their stable power supply and reliable communication offer unparalleled advantages. However, their motion planning is severely constrained by tether length limitations and entanglement risks, posing significant challenges to achieving optimal path planning. To address these challenges, this study introduces CDT-TCS (Convex Dissection Topology-based Tethered Configuration Search), a novel algorithm that leverages CDT Encoding as a homotopy invariant to represent topological states of paths. By integrating algebraic topology with geometric optimization, CDT-TCS efficiently computes the complete set of optimal feasible configurations for tethered robots at all positions in 2D environments through a single computation. Building on this foundation, we further propose three application-specific algorithms: i) CDT-TPP for optimal tethered path planning, ii) CDT-TMV for multi-goal visiting with tether constraints, iii) CDT-UTPP for distance-optimal path planning of untethered robots. All theoretical results and propositions underlying these algorithms are rigorously proven and thoroughly discussed in this paper. Extensive simulations demonstrate that the proposed algorithms significantly outperform state-of-the-art methods in their respective problem domains. Furthermore, real-world experiments on robotic platforms validate the practicality and engineering value of the proposed framework.

cs.RO↗

arXiv2025

Semiparametric Regression Models for Explanatory Variables with Missing Data due to Detection Limit

Detection limit (DL) has become an increasingly ubiquitous issue in statistical analyses of biomedical studies, such as cytokine, metabolite and protein analysis. In regression analysis, if an explanatory variable is left-censored due to concentrations below the DL, one may limit analyses to observed data. In many studies, additional, or surrogate, variables are available to model, and incorporating such auxiliary modeling information into the regression model can improve statistical power. Although methods have been developed along this line, almost all are limited to parametric models for both the regression and left-censored explanatory variable. While some recent work has considered semiparametric regression for the censored DL-effected explanatory variable, the regression of primary interest is still left parametric, which not only makes it prone to biased estimates, but also suffers from high computational cost and inefficiency due to maximizing an extremely complex likelihood function and bootstrap inference. In this paper, we propose a new approach by considering semiparametric generalized linear models (SPGLM) for the primary regression and parametric or semiparametric models for DL-effected explanatory variable. The semiparametric and semiparametric combination provides the most robust inference, while the semiparametric and parametric case enables more efficient inference. The proposed approach is also much easier to implement and allows for leveraging sample splitting and cross fitting (SSCF) to improve computational efficiency in variance estimation. In particular, our approach improves computational efficiency over bootstrap by 450 times. We use simulated and real study data to illustrate the approach.

stat.ME↗

arXiv2025

DLBAcalib: Robust Extrinsic Calibration for Non-Overlapping LiDARs Based on Dual LBA

Accurate extrinsic calibration of multiple LiDARs is crucial for improving the foundational performance of three-dimensional (3D) map reconstruction systems. This paper presents a novel targetless extrinsic calibration framework for multi-LiDAR systems that does not rely on overlapping fields of view or precise initial parameter estimates. Unlike conventional calibration methods that require manual annotations or specific reference patterns, our approach introduces a unified optimization framework by integrating LiDAR bundle adjustment (LBA) optimization with robust iterative refinement. The proposed method constructs an accurate reference point cloud map via continuous scanning from the target LiDAR and sliding-window LiDAR bundle adjustment, while formulating extrinsic calibration as a joint LBA optimization problem. This method effectively mitigates cumulative mapping errors and achieves outlier-resistant parameter estimation through an adaptive weighting mechanism. Extensive evaluations in both the CARLA simulation environment and real-world scenarios demonstrate that our method outperforms state-of-the-art calibration techniques in both accuracy and robustness. Experimental results show that for non-overlapping sensor configurations, our framework achieves an average translational error of 5 mm and a rotational error of 0.2°, with an initial error tolerance of up to 0.4 m/30°. Moreover, the calibration process operates without specialized infrastructure or manual parameter tuning. The code is open source and available on GitHub (\underline{https://github.com/Silentbarber/DLBAcalib})

cs.RO↗

arXiv2025

CoA: Towards Real Image Dehazing via Compression-and-Adaptation

Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore, there is an urgent need for an algorithm that excels in both efficiency and adaptability to address real image dehazing effectively. This work proposes a Compression-and-Adaptation (CoA) computational flow to tackle these challenges from a divide-and-conquer perspective. First, model compression is performed in the synthetic domain to develop a compact dehazing parameter space, satisfying efficiency demands. Then, a bilevel adaptation in the real domain is introduced to be fearless in unknown real environments by aggregating the synthetic dehazing capabilities during the learning process. Leveraging a succinct design free from additional constraints, our CoA exhibits domain-irrelevant stability and model-agnostic flexibility, effectively bridging the model chasm between synthetic and real domains to further improve its practical utility. Extensive evaluations and analyses underscore the approach's superiority and effectiveness. The code is publicly available at https://github.com/fyxnl/COA.

cs.CV↗

arXiv2025

Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting to downstream tasks remains challenging. Recent approaches attempt task-specific design but rarely achieve "The Best of Both Worlds" due to inconsistent optimization goals. To address these issues, we propose a novel method that leverages the semantic knowledge from the Segment Anything Model (SAM) to Grow the quality of fusion results and Enable downstream task adaptability, namely SAGE. Specifically, we design a Semantic Persistent Attention (SPA) Module that efficiently maintains source information via the persistent repository while extracting high-level semantic priors from SAM. More importantly, to eliminate the impractical dependence on SAM during inference, we introduce a bi-level optimization-driven distillation mechanism with triplet losses, which allow the student network to effectively extract knowledge. Extensive experiments show that our method achieves a balance between high-quality visual results and downstream task adaptability while maintaining practical deployment efficiency. The code is available at https://github.com/RollingPlain/SAGE_IVIF.

cs.CV↗