cs.CV

arXiv:2503.21836v1 Announce Type: new Abstract: Background: Chromosome karyotype analysis is crucial for diagnosing hereditary diseases, yet detecting structural abnormalities remains challenging. While AI has shown promise in medical imaging, its effectiveness varies across modalities. Leveraging advances in Foundation Models that integrate multimodal medical imaging for robust feature extraction and accurate diagnosis, we developed iMedImage, an end-to-end model for general medical image recognition, demonstrating strong performance across multiple imaging tasks, including chromosome abnormality detection. Materials and Methods: We constructed a comprehensive medical image dataset encompassing multiple modalities from common medical domains, including chromosome, cell, pathology, ultrasound, X-ray, CT, and MRI images. Based on this dataset, we developed the iMedImage model, which incorporates the following key features: (1) a unified representation method for diverse modality inputs and medical imaging tasks; (2) multi-level (case-level, image-level, patch-level) image recognition capabilities enhanced by Chain of Thought (CoT) embedding and Mixture of Experts (MoE) strategies. Results: The test set comprised data from 12 institutions across six regions in China, covering three mainstream scanning devices, and included naturally distributed, unscreened abnormal cases. On this diverse dataset, the model achieved a fully automated chromosome analysis workflow, including segmentation, karyotyping, and abnormality detection, reaching a sensitivity of 92.75% and a specificity of 91.5%. Conclusion: We propose iMedImage, an end-to-end foundation model for medical image analysis, demonstrating its superior performance across various medical imaging tasks. iMedImage provides clinicians with a precise imaging analysis tool and contributes to improving diagnostic accuracy and disease screening.

arXiv:2503.21886v1 Announce Type: new Abstract: High-fidelity reconstruction of head avatars from monocular videos is highly desirable for virtual human applications, but it remains a challenge in the fields of computer graphics and computer vision. In this paper, we propose a two-phase head avatar reconstruction network that incorporates a refined 3D mesh representation. Our approach, in contrast to existing methods that rely on coarse template-based 3D representations derived from 3DMM, aims to learn a refined mesh representation suitable for a NeRF that captures complex facial nuances. In the first phase, we train 3DMM-stored NeRF with an initial mesh to utilize geometric priors and integrate observations across frames using a consistent set of latent codes. In the second phase, we leverage a novel mesh refinement procedure based on an SDF constructed from the density field of the initial NeRF. To mitigate the typical noise in the NeRF density field without compromising the features of the 3DMM, we employ Laplace smoothing on the displacement field. Subsequently, we apply a second-phase training with these refined meshes, directing the learning process of the network towards capturing intricate facial details. Our experiments demonstrate that our method further enhances the NeRF rendering based on the initial mesh and achieves performance superior to state-of-the-art methods in reconstructing high-fidelity head avatars with such input.

arXiv:2503.21820v1 Announce Type: new Abstract: Image feature matching, a foundational task in computer vision, remains challenging for multimodal image applications, often necessitating intricate training on specific datasets. In this paper, we introduce a Unified Feature Matching pre-trained model (UFM) designed to address feature matching challenges across a wide spectrum of modal images. We present Multimodal Image Assistant (MIA) transformers, finely tunable structures adept at handling diverse feature matching problems. UFM exhibits versatility in addressing both feature matching tasks within the same modal and those across different modals. Additionally, we propose a data augmentation algorithm and a staged pre-training strategy to effectively tackle challenges arising from sparse data in specific modals and imbalanced modal datasets. Experimental results demonstrate that UFM excels in generalization and performance across various feature matching tasks. The code will be released at:https://github.com/LiaoYun0x0/UFM.

arXiv:2503.21830v1 Announce Type: new Abstract: Foundation models for 3D shape generation have recently shown a remarkable capacity to encode rich geometric priors across both global and local dimensions. However, leveraging these priors for downstream tasks can be challenging as real-world data are often scarce or noisy, and traditional fine-tuning can lead to catastrophic forgetting. In this work, we treat the weight space of a large 3D shape-generative model as a data modality that can be explored directly. We hypothesize that submanifolds within this high-dimensional weight space can modulate topological properties or fine-grained part features separately, demonstrating early-stage evidence via two experiments. First, we observe a sharp phase transition in global connectivity when interpolating in conditioning space, suggesting that small changes in weight space can drastically alter topology. Second, we show that low-dimensional reparameterizations yield controlled local geometry changes even with very limited data. These results highlight the potential of weight space learning to unlock new approaches for 3D shape generation and specialized fine-tuning.

arXiv:2503.21848v1 Announce Type: new Abstract: News videos require efficient content organisation and retrieval systems, but their unstructured nature poses significant challenges for automated processing. This paper presents a comprehensive comparative analysis of image, video, and audio classifiers for automated news video segmentation. This work presents the development and evaluation of multiple deep learning approaches, including ResNet, ViViT, AST, and multimodal architectures, to classify five distinct segment types: advertisements, stories, studio scenes, transitions, and visualisations. Using a custom-annotated dataset of 41 news videos comprising 1,832 scene clips, our experiments demonstrate that image-based classifiers achieve superior performance (84.34\% accuracy) compared to more complex temporal models. Notably, the ResNet architecture outperformed state-of-the-art video classifiers while requiring significantly fewer computational resources. Binary classification models achieved high accuracy for transitions (94.23\%) and advertisements (92.74\%). These findings advance the understanding of effective architectures for news video segmentation and provide practical insights for implementing automated content organisation systems in media applications. These include media archiving, personalised content delivery, and intelligent video search.

arXiv:2503.21860v1 Announce Type: new Abstract: Human hands play a central role in interacting, motivating increasing research in dexterous robotic manipulation. Data-driven embodied AI algorithms demand precise, large-scale, human-like manipulation sequences, which are challenging to obtain with conventional reinforcement learning or real-world teleoperation. To address this, we introduce ManipTrans, a novel two-stage method for efficiently transferring human bimanual skills to dexterous robotic hands in simulation. ManipTrans first pre-trains a generalist trajectory imitator to mimic hand motion, then fine-tunes a specific residual module under interaction constraints, enabling efficient learning and accurate execution of complex bimanual tasks. Experiments show that ManipTrans surpasses state-of-the-art methods in success rate, fidelity, and efficiency. Leveraging ManipTrans, we transfer multiple hand-object datasets to robotic hands, creating DexManipNet, a large-scale dataset featuring previously unexplored tasks like pen capping and bottle unscrewing. DexManipNet comprises 3.3K episodes of robotic manipulation and is easily extensible, facilitating further policy training for dexterous hands and enabling real-world deployments.

arXiv:2412.02545v3 Announce Type: replace Abstract: Shadows introduce challenges such as reduced brightness, texture deterioration, and color distortion in images, complicating a holistic solution. This study presents \textbf{ShadowHack}, a divide-and-conquer strategy that tackles these complexities by decomposing the original task into luminance recovery and color remedy. To brighten shadow regions and repair the corrupted textures in the luminance space, we customize LRNet, a U-shaped network with a rectified attention module, to enhance information interaction and recalibrate contaminated attention maps. With luminance recovered, CRNet then leverages cross-attention mechanisms to revive vibrant colors, producing visually compelling results. Extensive experiments on multiple datasets are conducted to demonstrate the superiority of ShadowHack over existing state-of-the-art solutions both quantitatively and qualitatively, highlighting the effectiveness of our design. Our code will be made publicly available.

arXiv:2503.21843v1 Announce Type: new Abstract: Human Activity Recognition (HAR) is a fundamental technology for numerous human - centered intelligent applications. Although deep learning methods have been utilized to accelerate feature extraction, issues such as multimodal data mixing, activity heterogeneity, and complex model deployment remain largely unresolved. The aim of this paper is to address issues such as multimodal data mixing, activity heterogeneity, and complex model deployment in sensor-based human activity recognition. We propose a spatiotemporal attention modal decomposition alignment fusion strategy to tackle the problem of the mixed distribution of sensor data. Key discriminative features of activities are captured through cross-modal spatio-temporal disentangled representation, and gradient modulation is combined to alleviate data heterogeneity. In addition, a wearable deployment simulation system is constructed. We conducted experiments on a large number of public datasets, demonstrating the effectiveness of the model.

arXiv:2503.21824v1 Announce Type: new Abstract: Recently, video-based large language models (video-based LLMs) have achieved impressive performance across various video comprehension tasks. However, this rapid advancement raises significant privacy and security concerns, particularly regarding the unauthorized use of personal video data in automated annotation by video-based LLMs. These unauthorized annotated video-text pairs can then be used to improve the performance of downstream tasks, such as text-to-video generation. To safeguard personal videos from unauthorized use, we propose two series of protective video watermarks with imperceptible adversarial perturbations, named Ramblings and Mutes. Concretely, Ramblings aim to mislead video-based LLMs into generating inaccurate captions for the videos, thereby degrading the quality of video annotations through inconsistencies between video content and captions. Mutes, on the other hand, are designed to prompt video-based LLMs to produce exceptionally brief captions, lacking descriptive detail. Extensive experiments demonstrate that our video watermarking methods effectively protect video data by significantly reducing video annotation performance across various video-based LLMs, showcasing both stealthiness and robustness in protecting personal video content. Our code is available at https://github.com/ttthhl/Protecting_Your_Video_Content.

arXiv:2503.21827v1 Announce Type: new Abstract: Edge detection remains a fundamental yet challenging task in computer vision, especially under varying illumination, noise, and complex scene conditions. This paper introduces a Hybrid Multi-Stage Learning Framework that integrates Convolutional Neural Network (CNN) feature extraction with a Support Vector Machine (SVM) classifier to improve edge localization and structural accuracy. Unlike conventional end-to-end deep learning models, our approach decouples feature representation and classification stages, enhancing robustness and interpretability. Extensive experiments conducted on benchmark datasets such as BSDS500 and NYUDv2 demonstrate that the proposed framework outperforms traditional edge detectors and even recent learning-based methods in terms of Optimal Dataset Scale (ODS) and Optimal Image Scale (OIS), while maintaining competitive Average Precision (AP). Both qualitative and quantitative results highlight enhanced performance on edge continuity, noise suppression, and perceptual clarity achieved by our method. This work not only bridges classical and deep learning paradigms but also sets a new direction for scalable, interpretable, and high-quality edge detection solutions.

arXiv:2503.21839v1 Announce Type: new Abstract: We investigate a critical yet under-explored question in Large Vision-Language Models (LVLMs): Do LVLMs genuinely comprehend interleaved image-text in the document? Existing document understanding benchmarks often assess LVLMs using question-answer formats, which are information-sparse and difficult to guarantee the coverage of long-range dependencies. To address this issue, we introduce a novel and challenging Multimodal Document Summarization Benchmark (M-DocSum-Bench), which comprises 500 high-quality arXiv papers, along with interleaved multimodal summaries aligned with human preferences. M-DocSum-Bench is a reference-based generation task and necessitates the generation of interleaved image-text summaries using provided reference images, thereby simultaneously evaluating capabilities in understanding, reasoning, localization, and summarization within complex multimodal document scenarios. To facilitate this benchmark, we develop an automated framework to construct summaries and propose a fine-grained evaluation method called M-DocEval. Moreover, we further develop a robust summarization baseline, i.e., M-DocSum-7B, by progressive two-stage training with diverse instruction and preference data. The extensive results on our M-DocSum-Bench reveal that the leading LVLMs struggle to maintain coherence and accurately integrate information within long and interleaved contexts, often exhibiting confusion between similar images and a lack of robustness. Notably, M-DocSum-7B achieves state-of-the-art performance compared to larger and closed-source models (including GPT-4o, Gemini Pro, Claude-3.5-Sonnet and Qwen2.5-VL-72B, etc.), demonstrating the potential of LVLMs for improved interleaved image-text understanding. The code, data, and models are available at https://github.com/stepfun-ai/M-DocSum-Bench.

arXiv:2503.21841v1 Announce Type: new Abstract: Advanced interpretation of hyperspectral remote sensing images benefits many precise Earth observation tasks. Recently, visual foundation models have promoted the remote sensing interpretation but concentrating on RGB and multispectral images. Due to the varied hyperspectral channels,existing foundation models would face image-by-image tuning situation, imposing great pressure on hardware and time resources. In this paper, we propose a tuning-free hyperspectral foundation model called HyperFree, by adapting the existing visual prompt engineering. To process varied channel numbers, we design a learned weight dictionary covering full-spectrum from $0.4 \sim 2.5 \, \mu\text{m}$, supporting to build the embedding layer dynamically. To make the prompt design more tractable, HyperFree can generate multiple semantic-aware masks for one prompt by treating feature distance as semantic-similarity. After pre-training HyperFree on constructed large-scale high-resolution hyperspectral images, HyperFree (1 prompt) has shown comparable results with specialized models (5 shots) on 5 tasks and 11 datasets.Code and dataset are accessible at https://rsidea.whu.edu.cn/hyperfree.htm.

arXiv:2503.21851v1 Announce Type: new Abstract: Traditional image classification requires a predefined list of semantic categories. In contrast, Large Multimodal Models (LMMs) can sidestep this requirement by classifying images directly using natural language (e.g., answering the prompt "What is the main object in the image?"). Despite this remarkable capability, most existing studies on LMM classification performance are surprisingly limited in scope, often assuming a closed-world setting with a predefined set of categories. In this work, we address this gap by thoroughly evaluating LMM classification performance in a truly open-world setting. We first formalize the task and introduce an evaluation protocol, defining various metrics to assess the alignment between predicted and ground truth classes. We then evaluate 13 models across 10 benchmarks, encompassing prototypical, non-prototypical, fine-grained, and very fine-grained classes, demonstrating the challenges LMMs face in this task. Further analyses based on the proposed metrics reveal the types of errors LMMs make, highlighting challenges related to granularity and fine-grained capabilities, showing how tailored prompting and reasoning can alleviate them.

arXiv:2503.21854v1 Announce Type: new Abstract: Instance segmentation is essential for augmented reality and virtual reality (AR/VR) as it enables precise object recognition and interaction, enhancing the integration of virtual and real-world elements for an immersive experience. However, the high computational overhead of segmentation limits its application on resource-constrained AR/VR devices, causing large processing latency and degrading user experience. In contrast to conventional scenarios, AR/VR users typically focus on only a few regions within their field of view before shifting perspective, allowing segmentation to be concentrated on gaze-specific areas. This insight drives the need for efficient segmentation methods that prioritize processing instance of interest, reducing computational load and enhancing real-time performance. In this paper, we present a foveated instance segmentation (FovealSeg) framework that leverages real-time user gaze data to perform instance segmentation exclusively on instance of interest, resulting in substantial computational savings. Evaluation results show that FSNet achieves an IoU of 0.56 on ADE20K and 0.54 on LVIS, notably outperforming the baseline. The code is available at https://github.com/SAI-

arXiv:2503.22179v1 Announce Type: new Abstract: Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression. Diffusion models, known for their superior generative capabilities, have recently shown promise in advancing face-swapping quality. This paper addresses two key challenges in diffusion-based face swapping: the prioritized preservation of identity over target attributes and the inherent conflict between identity and attribute conditioning. To tackle these issues, we introduce an identity-constrained attribute-tuning framework for face swapping that first ensures identity preservation and then fine-tunes for attribute alignment, achieved through a decoupled condition injection. We further enhance fidelity by incorporating identity and adversarial losses in a post-training refinement stage. Our proposed identity-constrained diffusion-based face-swapping model outperforms existing methods in both qualitative and quantitative evaluations, demonstrating superior identity similarity and attribute consistency, achieving a new state-of-the-art performance in high-fidelity face swapping.

arXiv:2409.07067v3 Announce Type: replace Abstract: Spacecraft image denoising is a crucial fundamental technology closely related to aerospace research. However, the existing deep learning-based image denoising methods are primarily designed for natural image and fail to adequately consider the characteristics of spacecraft image(e.g. low-light conditions, repetitive periodic structures), resulting in suboptimal performance in the spacecraft image denoising task. To address the aforementioned problems, we propose a Structure modeling Activation Free Fourier Network (SAFFN), which is an efficient spacecraft image denoising method including Structure Modeling Block (SMB) and Activation Free Fourier Block (AFFB). We present SMB to effectively extract edge information and model the structure for better identification of spacecraft components from dark regions in spacecraft noise image. We present AFFB and utilize an improved Fast Fourier block to extract repetitive periodic features and long-range information in noisy spacecraft image. Extensive experimental results demonstrate that our SAFFN performs competitively compared to the state-of-the-art methods on spacecraft noise image datasets. The codes are available at: https://github.com/shenduke/SAFFN.

arXiv:2503.21834v1 Announce Type: new Abstract: Accurate vessel trajectory prediction facilitates improved navigational safety, routing, and environmental protection. However, existing prediction methods are challenged by the irregular sampling time intervals of the vessel tracking data from the global AIS system and the complexity of vessel movement. These aspects render model learning and generalization difficult. To address these challenges and improve vessel trajectory prediction, we propose the multi-modal knowledge-enhanced framework (MAKER) for vessel trajectory prediction. To contend better with the irregular sampling time intervals, MAKER features a Large language model-guided Knowledge Transfer (LKT) module that leverages pre-trained language models to transfer trajectory-specific contextual knowledge effectively. To enhance the ability to learn complex trajectory patterns, MAKER incorporates a Knowledge-based Self-paced Learning (KSL) module. This module employs kinematic knowledge to progressively integrate complex patterns during training, allowing for adaptive learning and enhanced generalization. Experimental results on two vessel trajectory datasets show that MAKER can improve the prediction accuracy of state-of-the-art methods by 12.08%-17.86%.

arXiv:2503.21817v1 Announce Type: new Abstract: Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding. We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models. On top of conventional token compression approaches, our method introduces two complementary acceleration strategies. For training acceleration, we observe that Feed-Forward Network (FFN) computations on visual tokens induce marginal feature updates. This motivates our Skip-FFN strategy, which bypasses FFN layers for redundant visual tokens. For inference acceleration, we design a selective KV-cache removal mechanism that prunes the skipped key-value pairs during decoding while preserving model performance. Experimental results demonstrate that Skip-Vision reduces training time by up to 35\%, inference FLOPs by 75\%, and latency by 45\%, while achieving comparable or superior performance to existing methods. Our work provides a practical solution for scaling high-performance MLLMs with enhanced efficiency.

arXiv:2503.21823v1 Announce Type: new Abstract: Traditional range-instantaneous Doppler (RID) methods for rigid-body target imaging often suffer from low resolution due to the limitations of time-frequency analysis (TFA). To address this challenge, our primary focus is on obtaining high resolution time-frequency representations (TFRs) from their low resolution counterparts. Recognizing that the curve features of TFRs are a specific type of texture feature, we argue that pre trained generative models such as Stable Diffusion (SD) are well suited for enhancing TFRs, thanks to their powerful capability in capturing texture representations. Building on this insight, we propose a novel inverse synthetic aperture radar (ISAR) imaging method for rigid-body targets, leveraging the low-rank adaptation (LoRA) of a pre-trained SD model. Our approach adopts the basic structure and pre-trained parameters of SD Turbo while incorporating additional linear operations for LoRA and adversarial training to achieve super-resolution and noise suppression. Then we integrate LoRA-SD into the RID-based ISAR imaging, enabling sharply focused and denoised imaging with super-resolution capabilities. We evaluate our method using both simulated and real radar data. The experimental results demonstrate the superiority of our approach in frequency es timation and ISAR imaging compared to traditional methods. Notably, the generalization capability is verified by training on simulated radar data and testing on measured radar data.

arXiv:2503.21889v1 Announce Type: new Abstract: Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and system integrations. Despite being widely used, building workflows can be complex, often requiring manual configuration through low-code platforms or visual programming tools. To simplify this process, we explore the use of generative foundation models, particularly vision-language models (VLMs), to automatically generate structured workflows from visual inputs. Translating hand-drawn sketches or computer-generated diagrams into executable workflows is challenging due to the ambiguity of free-form drawings, variations in diagram styles, and the difficulty of inferring execution logic from visual elements. To address this, we introduce StarFlow, a framework for generating structured workflow outputs from sketches using vision-language models. We curate a diverse dataset of workflow diagrams -- including synthetic, manually annotated, and real-world samples -- to enable robust training and evaluation. We finetune and benchmark multiple vision-language models, conducting a series of ablation studies to analyze the strengths and limitations of our approach. Our results show that finetuning significantly enhances structured workflow generation, outperforming large vision-language models on this task.