论文检索

Junle Liu, Peirong Zhang, Yuyi Zhang, Pengyu Yan, Hui Zhou, Xinyue Zhou, Fengjun Guo, Lianwen Jin

Commercial-grade poster design demands the seamless integration of aesthetic appeal with precise, informative content delivery. Current automated poster generation systems face significant limitations, including incomplete design workflows, poor text rendering accuracy, and insufficient flexibility for commercial applications. To address these challenges, we propose PosterVerse, a full-workflow, commercial-grade poster generation method that seamlessly automates the entire design process while delivering high-density and scalable text rendering. PosterVerse replicates professional design through three key stages: (1) blueprint creation using fine-tuned LLMs to extract key design elements from user requirements, (2) graphical background generation via customized diffusion models to create visually appealing imagery, and (3) unified layout-text rendering with an MLLM-powered HTML engine to guarantee high text accuracy and flexible customization. In addition, we introduce PosterDNA, a commercial-grade, HTML-based dataset tailored for training and validating poster design models. To the best of our knowledge, PosterDNA is the first Chinese poster generation dataset to introduce HTML typography files, enabling scalable text rendering and fundamentally solving the challenges of rendering small and high-density text. Experimental results demonstrate that PosterVerse consistently produces commercial-grade posters with appealing visuals, accurate text alignment, and customizable layouts, making it a promising solution for automating commercial poster design.

Jiaxin Liu, Zhaolu Kang

While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video understanding. We introduce ReasonAct, a method that enhances video reasoning in smaller models through a three-stage training process: first building a foundation with text-only reasoning, then fine-tuning on video, and finally refining with temporal-aware reinforcement learning. We build upon Temporal Group Relative Policy Optimization (T-GRPO) by incorporating temporal consistency modeling into policy optimization. We also propose a biomechanically-motivated sub-action decomposition mechanism that provides graduated rewards for constituent action phases. Through experiments on HMDB51, UCF-101, and Kinetics-400, our 3B-parameter model achieves 67.2%, 94.1%, and 78.9% accuracy respectively, demonstrating improvements of 17.9, 15.8, and 12.3 points over baselines. Ablation studies validate that our progressive training enables smaller models to achieve competitive video reasoning performance while maintaining computational efficiency.

Jiaxin Liu, Gangwei Xu, Xianqi Wang, Chengliang Zhang, Xin Yang

Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular foundation models (MFMs) to improve generalization, but typically suffer from substantial inference latency. To address this trade-off, we propose Generalized Geometry Encoding Volume (GGEV), a novel real-time stereo matching network that achieves strong generalization. We first extract depth-aware features that encode domain-invariant structural priors as guidance for cost aggregation. Subsequently, we introduce a Depth-aware Dynamic Cost Aggregation (DDCA) module that adaptively incorporates these priors into each disparity hypothesis, effectively enhancing fragile matching relationships in unseen scenes. Both steps are lightweight and complementary, leading to the construction of a generalized geometry encoding volume with strong generalization capability. Experimental results demonstrate that our GGEV surpasses all existing real-time methods in zero-shot generalization capability, and achieves state-of-the-art performance on the KITTI 2012, KITTI 2015, and ETH3D benchmarks.

Jiaqi Liu, Ronghao Fu, Lang Sun, Haoran Liu, Xiao Yang, Weipeng Zhang, Xu Na, Zhuoran Duan, Bo Yang

The emergence of large vision-language models (VLMs) has significantly enhanced the efficiency and flexibility of geospatial interpretation. However, general-purpose VLMs remain suboptimal for remote sensing (RS) tasks. Existing geospatial VLMs typically adopt a unified modeling strategy and struggle to differentiate between task types and interpretation granularities, limiting their ability to balance local detail perception and global contextual understanding. In this paper, we present SkyMoE, a Mixture-of-Experts (MoE) vision-language model tailored for multimodal, multi-task RS interpretation. SkyMoE employs an adaptive router that generates task- and granularity-aware routing instructions, enabling specialized large language model experts to handle diverse sub-tasks. To further promote expert decoupling and granularity sensitivity, we introduce a context-disentangled augmentation strategy that creates contrastive pairs between local and global features, guiding experts toward level-specific representation learning. We also construct MGRS-Bench, a comprehensive benchmark covering multiple RS interpretation tasks and granularity levels, to evaluate generalization in complex scenarios. Extensive experiments on 21 public datasets demonstrate that SkyMoE achieves state-of-the-art performance across tasks, validating its adaptability, scalability, and superior multi-granularity understanding in remote sensing.

Jia Liu, Qian Li, Yongqi Li, Cheng Ji, Shangguang Wang

Satellite-acquired optical remote sensing imagery is extensively applied in time-critical applications like traffic surveillance and evaluation of natural disasters. However, clouds, as a common atmospheric phenomenon, frequently obscure observation. Current approaches aim to restore visibility in cloud-obscured regions, yet they typically fall short in the presence of dense cloud cover, which are exceedingly prevalent in remote sensing imagery. Alternative approaches rely on the satellite revisit cycle, frequently surpassing ten days, a duration impractical for genuine application scenarios due to target changes and bandwidth limitations. To address these issues, this paper proposes SCo-Cloud, a novel satellite constellation collaboration framework for cloud-aware onboard-computed imaging and transmission, which consists of Center-Sat and Edge-Sats. We propose onboard thin cloud removal and re-imaging region location models to locate the impact of clouds. We further design a novel multi-satellite scheduling strategy to eliminate clouds. The models above are integrated within the Center-Sat, with the nearby Edge-Sats collaborating in tandem to execute re-imaging assignments. Furthermore, to facilitate in-depth research, we have meticulously developed a cloud-covered target detection dataset. Comprehensive experiments have conclusively demonstrated that SCo-Cloud effectively surpasses the limitations inherent in current approaches, providing accurate and timely responses within the domain of Earth observation.

Hangyu Liu, Bo Peng, Pengxiang Ding, Donglin Wang

Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches for multi-target attacks primarily encode target labels into one-dimensional tensors, leading to a loss of fine-grained visual information and overfitting to model-specific features during noise generation. To address this gap, we first identify and validate that the semantic feature quality and quantity are critical factors affecting the transferability of targeted attacks: 1) Feature quality refers to the structural and detailed completeness of the implanted target features, as deficiencies may result in the loss of key discriminative information; 2) Feature quantity refers to the spatial sufficiency of the implanted target features, as inadequacy limits the victim model's attention to this feature. Based on these findings, we propose the 2D Tensor-Guided Adversarial Fusion (TGAF) framework, which leverages the powerful generative capabilities of diffusion models to encode target labels into two-dimensional semantic tensors for guiding adversarial noise generation. Additionally, we design a novel masking strategy tailored for the training process, ensuring that parts of the generated noise retain complete semantic information about the target class. Extensive experiments demonstrate that TGAF consistently surpasses state-of-the-art methods across various settings.

Han Liu, Hengyu Man, Xingtao Wang, Wenrui Li, Debin Zhao

Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces via convolutional neural networks (CNNs) or Swin Transformers, which tend to retain substantial spatial redundancy, thereby limiting overall compression performance. In this paper, we propose a novel Mixed RWKV-Transformer (MRT) architecture that encodes images into more compact 1-D latent representations by synergistically integrating the complementary strengths of linear-attention-based RWKV and self-attention-based Transformer models. Specifically, MRT partitions each image into fixed-size windows, utilizing RWKV modules to capture global dependencies across windows and Transformer blocks to model local redundancies within each window. The hierarchical attention mechanism enables more efficient and compact representation learning in the 1-D domain. To further enhance compression efficiency, we introduce a dedicated RWKV Compression Model (RCM) tailored to the structure characteristics of the intermediate 1-D latent features in MRT. Extensive experiments on standard image compression benchmarks validate the effectiveness of our approach. The proposed MRT framework consistently achieves superior reconstruction quality at bitrates below 0.02 bits per pixel (bpp). Quantitative results based on the DISTS metric show that MRT significantly outperforms the state-of-the-art 2-D architecture GLC, achieving bitrate savings of 43.75%, 30.59% on the Kodak and CLIC2020 test datasets, respectively.

Fengchun Liu, Songhan Jiang, Linghan Cai, Ziyue Wang, Yongbing Zhang

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding. Existing alignment methods struggle to capture fine-grained correspondences between textual descriptions and visual cues across thousands of patches from a slide, compromising their performance on downstream tasks. In this paper, we propose PathFLIP (Pathology Fine-grained Language-Image Pretraining), a novel framework for holistic WSI interpretation. PathFLIP decomposes slide-level captions into region-level sub-captions and generates text-conditioned region embeddings to facilitate precise visual-language grounding. By harnessing Large Language Models (LLMs), PathFLIP can seamlessly follow diverse clinical instructions and adapt to varied diagnostic contexts. Furthermore, it exhibits versatile capabilities across multiple paradigms, efficiently handling slide-level classification and retrieval, fine-grained lesion localization, and instruction following. Extensive experiments demonstrate that PathFLIP outperforms existing large-scale pathological VLMs on four representative benchmarks while requiring significantly less training data, paving the way for fine-grained, instruction-aware WSI interpretation in research and clinical practice.

Delong Liu, Haotian Hou, Zhaohui Hou, Shihao Han, Zhiyuan Huang, Mingjie Zhan, Fei Su, Zhicheng Zhao

Precise and controllable image editing, especially object removal and insertion, represents one of the most common demands in image manipulation. However, existing methods suffer from severe limitations. Mask-based inpainting often introduces visual artifacts and semantic inconsistencies, while instruction-based approaches lack accurate spatial control and tend to unintentionally modify background regions. To address these issues, we propose two key contributions. First, we develop a fully automated and self-improving pipeline for synthetic data generation. This pipeline utilizes a Large Language Model (LLM) to generate diverse prompts, a Diffusion Transformer (DiT) fine-tuned evolutionarily to synthesize high-quality images, and a Multimodal LLM (MLLM) combined with open-set object detector for automated quality control and annotation. This process produces the Remove/Add Dataset (RAD), consisting of over 514,510 high-quality image pairs, each richly annotated with bounding boxes, segmentation masks, and a variety of editing instructions. Second, based on RAD, we introduce Remove/Add Anything (RAA), a novel editing framework with precise spatial control. Built upon a diffusion-based inpainting model, RAA achieves high editing accuracy by conditioning on both textual instructions and an explicitly defined region of interest (ROI), enabling efficient fine-tuning while maintaining global visual coherence. Extensive experiments demonstrate that RAA significantly outperforms existing open-source methods on both addition and removal tasks, and even slightly surpasses costly proprietary models.

Daizong Liu, Baoquan Chen, Wei Hu

Although large vision-language models (LVLMs) have demonstrated promising versatile capabilities on various downstream tasks, they are shown to be susceptible to adversarial examples. Existing LVLM attackers simply implement adversarial patterns in an impracticable setting: i) add digital global perturbations to entire input image; ii) access prior knowledge of LVLMs for optimization; iii) do not consider realistic transformations. These make them difficult to deploy in the physical-world attack scenarios. Motivated by the research gap and counter-practice phenomenon, this paper proposes the first practical LVLM attack method based on a novel adversarial patch design, which can achieve physical and digital attack settings without using any LVLM details. In particular, we introduce adversarial homogeneous constraints in both spatial and spectral domains to improve the patch stealthy for resisting potential real-world defenses. Besides, we also develop a new technique for synthesizing reasonably realistic transformations that capture the expected patch appearance variations in daily life. Extensive experiments are conducted to verify the strong adversarial capabilities of our proposed attack against prevalent LVLMs spanning a spectrum of tasks.

Daixian Liu, Hau-Sing So, Haoran Chen, Jiao Li, Shanshan Wang, Mengzhu Wang, Jingcai Guo

Spatial multi-modal omics technologies have transformed biological research by enabling the simultaneous profiling of gene expression, protein abundance, and chromatin accessibility within their native spatial contexts. Despite these advances, accurately clustering rare cell types remains a major challenge due to data sparsity, high dimensionality, and limited annotated samples. While Graph Neural Networks (GNNs) have shown potential in modeling spatial omics data, their effectiveness is often constrained by the use of fixed K-nearest neighbor (KNN) graph structures, which fail to capture latent semantic relationships masked by sequencing noise. To overcome these limitations, we propose CRCT (Clustering Rare Cell Types): a novel framework that combines Implicit Semantic Data Augmentation (ISDA) with adaptive graph learning for spatial multi-modal omics analysis. Unlike traditional augmentation strategies that generate explicit synthetic samples, CRCT operates in the deep feature space by dynamically estimating intra-class covariance matrices and implicitly perturbing features along semantically meaningful directions. This enables effective augmentation for rare cell populations while preserving biological fidelity. Extensive experiments across four real-world datasets (HLN, MB, Stereo‑CITE‑seq, and SPOTS) and one synthetic benchmark demonstrate the state-of-the-art performance of CRCT, achieving improvements of up to +1.7 NMI and +7.8 ARI over strong baseline methods.

Chong Liu, Xun Jiang, Fumin Shen, Lei Zhu, Jingkuan Song, Heng Tao Shen, Xing Xu

Natural Language-based Egocentric Task Verification (NLETV) aims to verify the alignment between action sequences in egocentric videos and their corresponding textual descriptions. However, existing NLETV approaches are still facing two critical challenges: (1) These methods are designed for simulating environments, ignoring the domain gap between synthetic and realistic data. (2) The matching processes are regarded as a simple binary classification problem, which undermines model reliability due to evaluation bias and uncalibrated decision settings. To address these challenges, we propose a novel method termed Prototypical Evidential Learning (PEL), which can be adapted to existing NLETV approaches and boost the model generalization and mitigate prediction bias. Our method leverages prototypes to guide cross-domain alignment and evidence collection. Specifically, PEL consists of two key components: (1) Prototypical Domain Adaptation module enabling cross-domain feature alignment and intra-domain prototype preservation between synthetic and realistic domains; (2) Matching Evidence Collector module, which quantifies prediction uncertainty on the prototypical representations through evidential deep learning. It enforces the model to collect the vision-text consistency and discrepancy evidence, thus addressing the issues of biased decisions in binary classification. Extensive experiments on two public datasets demonstrate that our PEL method outperforms existing state-of-the-art NLETV methods and shows remarkable generalizability.

Chi Liu, Jincheng Liu, Congcong Zhu, Minghao Wang, Sheng Shen, Jia Gu, Tianqing Zhu, Wanlei Zhou

Developing Medical AI relies on large datasets and easily suffers from data scarcity. Generative data augmentation (GDA) using AI generative models offers a solution to synthesize realistic medical images. However, the bias in GDA is often underestimated in medical domains, with concerns about the risk of introducing detrimental features generated by AI and harming downstream tasks. This paper identifies the frequency misalignment between real and synthesized images as one of the key factors underlying unreliable GDA and proposes the Frequency Recalibration (FreRec) method to reduce the frequency distributional discrepancy and thus improve GDA. FreRec involves (1) Statistical High-frequency Replacement (SHR) to roughly align high-frequency components and (2) Reconstructive High-frequency Mapping (RHM) to enhance image quality and reconstruct high-frequency details. Extensive experiments were conducted in various medical datasets, including brain MRIs, chest X-rays, and fundus images. The results show that FreRec significantly improves downstream medical image classification performance compared to uncalibrated AI-synthesized samples. FreRec is a standalone post-processing step that is compatible with any generative model and can integrate seamlessly with common medical GDA pipelines.

Chen Liu, Wen Li, Yongshu Huang, Minghang Zhu, Yuyang Yang, Dunqiang Liu, Sheng Ao, Cheng Wang

LiDAR odometry is a critical component of SLAM in autonomous driving and robotics. Learning-based methods have shown remarkable performance by regressing relative poses in an end-to-end manner. However, when applying these trained models, originally developed on the widely used KITTI dataset, to other scenes, performance often drops significantly. In other words, existing methods struggle to generalize well to new environments. To address this challenge, we propose RCP-LO, a simple yet effective LiDAR odometry framework. We introduce a novel representation for relative poses, reformulating them as relative coordinates, which can then be solved using geometrical verification. This approach avoids overly simplified pose representations and makes better use of scene geometry, thereby improving generalization. Moreover, to capture the inherent uncertainties in relative pose estimation from occluded LiDAR point clouds from dynamic environments, we adapt our framework to learn a denoising diffusion model, allowing for sampling plausible relative coordinates while improving robustness. We also introduce a differentiable geometric weighted singular value decomposition module, enabling efficient pose estimation through a single forward pass. Extensive experiments demonstrate that RCP-LO, trained exclusively on the KITTI dataset, achieves competitive performance compared to SOTA learning-based methods and generalizes effectively to the KITTI-360, Ford, and Oxford datasets.

Bo Liu, Qiao Qin, Qinghui He

The rapid advancement of generative models has increased the demand for generated image detectors capable of generalizing across diverse and evolving generation techniques. However, existing methods, including those leveraging pre-trained vision-language models, often produce highly entangled representations, mixing task-relevant forensic cues (causal features) with spurious or irrelevant patterns (non-causal features), thus limiting generalization. To address this issue, we propose CausalCLIP, a framework that explicitly disentangles causal from non-causal features and employs targeted filtering guided by causal inference principles to retain only the most transferable and discriminative forensic cues. By modeling the generation process with a structural causal model and enforcing statistical independence through Gumbel-Softmax-based feature masking and Hilbert-Schmidt Independence Criterion (HSIC) constraints, CausalCLIP isolates stable causal features robust to distribution shifts. When tested on unseen generative models from different series, CausalCLIP demonstrates strong generalization ability, achieving improvements of 6.83% in accuracy and 4.06% in average precision over state-of-the-art methods.

Aoran Liu, Kun Hu, Clinton Ansun Mo, Qiuxia Wu, Wenxiong Kang, Zhiyong Wang

Garment simulation is fundamental to various applications in computer vision and graphics, from virtual try-on to digital human modelling. However, conventional physics-based methods remain computationally expensive, hindering their application in time-sensitive scenarios. While graph neural networks (GNNs) offer promising acceleration, existing approaches exhibit poor cross-resolution generalisation, demonstrating significant performance degradation on higher-resolution meshes beyond the training distribution. This stems from two key factors: (1) existing GNNs employ fixed message-passing depth that fails to adapt information aggregation to mesh density variation, and (2) vertex-wise displacement magnitudes are inherently resolution-dependent in garment simulation. To address these issues, we introduce Propagation-before-Update Graph Network (Pb4U-GNet), a resolution-adaptive framework that decouples message propagation from feature updates. Pb4U-GNet incorporates two key mechanisms: (1) dynamic propagation depth control, adjusting message-passing iterations based on mesh resolution, and (2) geometry-aware update scaling, which scales predictions according to local mesh characteristics. Extensive experiments show that even trained solely on low-resolution meshes, Pb4U-GNet exhibits strong generalisability across diverse mesh resolutions, addressing a fundamental challenge in neural garment simulation.

Junjie Linghu, Qiang Ling

3D street scene reconstruction is a challenging yet crucial task for autonomous driving. Many reconstruction methods often overlook two key limitations for high-quality driving scene reconstruction, sensitivity to camera parameter noise from high-speed vehicles and heavy reliance on precise dynamic object annotations of datasets. To resolve these issues, we propose DenoiseGS, a simple yet effective approach based on explicit 3D Gaussian splatting. Specifically, we propose a novel learnable Delta attribute per Gaussian primitive that operates on the image plane during rasterization to mitigate the impact of noisy camera parameters through modulating the inputs of the alpha-blending process. To enhance the representation of this Delta attribute, we propose a DeltaEstimator that encodes viewing direction and contextual cues to facilitate view dependence. We also extend additional CUDA operations to enable efficient gradient update for the delta attribute. Furthermore, to overcome the limitation of inaccurate annotations for dynamic objects, we propose a learnable B-spline trajectory optimization with a few control points to model the trajectory of a moving object. Comprehensive experiments conducted on nuScenes and Waymo Open Dataset demonstrate that our DenoiseGS outperforms some state-of-the-art methods across all metrics of both reconstruction quality and novel view synthesis.

Yongguo Ling, Chen Zhang, Yiming Liu, Wenhao Shao

Cross-time vehicle re-identification (Re-ID), especially across day and night conditions, remains a challenging problem due to drastic illumination variations that lead to significant domain shifts. While existing methods perform well under daytime scenarios, their effectiveness degrades severely in cross-domain settings, and fully supervised solutions demand costly annotations in both domains. In this paper, we introduce a new setting, Unsupervised Day-Night Vehicle Re-Identification (USL-DN-ReID), and propose a novel Cluster-Instance Alignment (CIA) framework to address it. CIA performs dual-level alignment: 1) at the cluster level, a Dictionary-Guided Graph Matching (DGM) module builds a cross-domain topological graph using soft similarities among cluster centers and solves global matching via the Hungarian algorithm; 2) at the instance level, a Multi-Factor Adaptive Alignment (MAA) module introduces a multi-factor adaptive weighting strategy that emphasizes high-confidence pairwise relations while suppressing noise. Together, these components enable robust and scalable cross-domain adaptation without requiring target-domain labels. Extensive experiments conducted on the DN-348 and DN-Wild benchmarks demonstrate the effectiveness and superiority of the proposed CIA framework, setting new state-of-the-art results on both datasets.

Run Ling, Ke Cao, Jian Lu, Ao Ma, Haowei Liu, Runze He, Changwei Wang, Rongtao Xu, Yihua Shao, Zhanjie Zhang 等

Multi-subject video generation aims to synthesize videos from textual prompts and multiple reference images, ensuring that each subject preserves natural scale and visual fidelity. However, current methods face two challenges: scale inconsistency, where variations in subject size lead to unnatural generation, and permutation sensitivity, where the order of reference inputs causes subject distortion. In this paper, we propose MoFu, a unified framework that tackles both challenges. For scale inconsistency, we introduce Scale-Aware Modulation (SMO), an LLM-guided module that extracts implicit scale cues from the prompt and modulates features to ensure consistent subject sizes. To address permutation sensitivity, we present a simple yet effective Fourier Fusion strategy that processes the frequency information of reference features via the Fast Fourier Transform to produce a unified representation. Besides, we design a Scale-Permutation Stability Loss to jointly encourage scale-consistent and permutation-invariant generation. To further evaluate these challenges, we establish a dedicated benchmark with controlled variations in subject scale and reference permutation. Extensive experiments demonstrate that MoFu significantly outperforms existing methods in preserving natural scale, subject fidelity, and overall visual quality.

Zheng Lin, Nan Zhou, Yuhan Wang, Bojian Zhang

Interactive segmentation aims to delineate a user-specified target in an image by leveraging positive and negative clicks. While effective on natural images, existing methods often fail in remote sensing scenarios, where satellite imagery is characterized by ultra-high resolution, sparse object distribution, and significant scale variation. These factors hinder accurate segmentation of fine-grained targets like roads, buildings, and aircraft. To overcome these problems, we propose CrossCut, a novel interactive segmentation framework tailored for remote sensing imagery. Unlike previous approaches that either process the entire image or treat each patch independently, CrossCut enables simultaneous segmentation across multiple patches by propagating user click information to all patches. This design allows the model to fully utilize click guidance regardless of object location, effectively resolving the challenge of inter-patch information isolation. Furthermore, CrossCut supports flexible inference by allowing segmentation results from different patch configurations to be fused, enhancing both accuracy and robustness. Extensive evaluations across multiple remote sensing datasets demonstrate that CrossCut achieves state-of-the-art performance. Quantitative results and visualizations show that CrossCut significantly advances the field of interactive segmentation for remote sensing imagery.