The integration of Large Language Models (LLMs) with computer vision is profoundly transforming perception tasks like image segmentation. For intelligent transportation systems (ITS), where accurate scene understanding is critical for safety and efficiency, this new paradigm offers unprecedented capabilities. This survey systematically reviews the emerging field of LLM-augmented image segmentation, focusing on its applications, challenges, and future directions within ITS. We provide a taxonomy of current approaches based on their prompting mechanisms and core architectures, and we highlight how these innovations can enhance road scene understanding for autonomous driving, traffic monitoring, and infrastructure maintenance. Finally, we identify key challenges, including real-time performance and safety-critical reliability, and outline a perspective centered on explainable, human-centric AI as a prerequisite for the successful deployment of this technology in next-generation transportation systems.
Semi-supervised semantic segmentation remains challenging under severe label scarcity and domain variability. Vision-only methods often struggle to generalize, resulting in pixel misclassification between similar classes, poor generalization and boundary localization. Vision-Language Models offer robust, domain-invariant semantics but lack the spatial grounding required for dense prediction. We introduce HierVL, a unified framework that bridges this gap by integrating abstract text embeddings into a mask-transformer architecture tailored for semi-supervised segmentation. HierVL features three novel components: a Hierarchical Semantic Query Generator that filters and projects abstract class embeddings into multi-scale queries to suppress irrelevant classes and handle intra-class variability; a Cross-Modal Spatial Alignment Module that aligns semantic queries with pixel features for sharper boundaries under sparse supervision; and a Dual-Query Transformer Decoder that fuses semantic and instance-level queries to prevent instance collapse. We also introduce targeted regularization losses that maintain vision-language alignment throughout training to reinforce semantic grounding. HierVL establishes a new state-of-the-art by achieving a +4.4% mean improvement of the intersection over the union on COCO (with 232 labeled images), +3.1% on Pascal VOC (with 92 labels), +5.9% on ADE20 (with 158 labels) and +1.8% on Cityscapes (with 100 labels), demonstrating better performance under 1% supervision on four benchmark datasets. Our results show that language-guided segmentation closes the label efficiency gap and unlocks new levels of fine-grained, instance-aware generalization.
This paper presents VisLanding, a monocular 3D perception-based framework for safe UAV (Unmanned Aerial Vehicle) landing. Addressing the core challenge of autonomous UAV landing in complex and unknown environments, this study innovatively leverages the depth-normal synergy prediction capabilities of the Metric3D V2 model to construct an end-to-end safe landing zones (SLZ) estimation framework. By introducing a safe zone segmentation branch, we transform the landing zone estimation task into a binary semantic segmentation problem. The model is fine-tuned and annotated using the WildUAV dataset from a UAV perspective, while a cross-domain evaluation dataset is constructed to validate the model's robustness. Experimental results demonstrate that VisLanding significantly enhances the accuracy of safe zone identification through a depth-normal joint optimization mechanism, while retaining the zero-shot generalization advantages of Metric3D V2. The proposed method exhibits superior generalization and robustness in cross-domain testing compared to other approaches. Furthermore, it enables the estimation of landing zone area by integrating predicted depth and normal information, providing critical decision-making support for practical applications.
Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance, balancing accuracy and real-time inference remains a challenge. To address this, we propose a logits-based knowledge distillation framework for MOS, aiming to improve accuracy while maintaining real-time efficiency. Specifically, we adopt a Bird's Eye View (BEV) projection-based model as the student and a non-projection model as the teacher. To handle the severe imbalance between moving and non-moving classes, we decouple them and apply tailored distillation strategies, allowing the teacher model to better learn key motion-related features. This approach significantly reduces false positives and false negatives. Additionally, we introduce dynamic upsampling, optimize the network architecture, and achieve a 7.69% reduction in parameter count, mitigating overfitting. Our method achieves a notable IoU of 78.8% on the hidden test set of the SemanticKITTI-MOS dataset and delivers competitive results on the Apollo dataset. The KDMOS implementation is available at https://github.com/SCNU-RISLAB/KDMOS.
Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unknown object instances. In this work, we propose ULOPS, an uncertainty-guided open-set panoptic segmentation framework that leverages Dirichlet-based evidential learning to model predictive uncertainty. Our architecture incorporates separate decoders for semantic segmentation with uncertainty estimation, embedding with prototype association, and instance center prediction. During inference, we leverage uncertainty estimates to identify and segment unknown instances. To strengthen the model's ability to differentiate between known and unknown objects, we introduce three uncertainty-driven loss functions. Uniform Evidence Loss to encourage high uncertainty in unknown regions. Adaptive Uncertainty Separation Loss ensures a consistent difference in uncertainty estimates between known and unknown objects at a global scale. Contrastive Uncertainty Loss refines this separation at the fine-grained level. To evaluate open-set performance, we extend benchmark settings on KITTI-360 and introduce a new open-set evaluation for nuScenes. Extensive experiments demonstrate that ULOPS consistently outperforms existing open-set LiDAR panoptic segmentation methods.
Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction uncertainty. Current approaches often discard uncertain regions through strict thresholding favouring dominant classes. To address these limitations, we introduce a holistic framework that transforms uncertainty into a learning asset through four principal components: (1) fuzzy pseudo-labeling, which preserves soft class distributions from top-K predictions to enrich supervision; (2) uncertainty-aware dynamic weighting, that modulate pixel-wise contributions via entropy-based reliability scores; (3) adaptive class rebalancing, which dynamically adjust losses to counteract long-tailed class distributions; and (4) lightweight contrastive regularization, that encourage compact and discriminative feature embeddings. Extensive experiments on benchmarks demonstrate that our method outperforms current state-of-the-art approaches, achieving significant improvements in the segmentation of under-represented classes and ambiguous regions.
This paper presents Segment This Thing (STT), a new efficient image segmentation model designed to produce a single segment given a single point prompt. Instead of following prior work and increasing efficiency by decreasing model size, we gain efficiency by foveating input images. Given an image and a point prompt, we extract a crop centered on the prompt and apply a novel variable-resolution patch tokenization in which patches are downsampled at a rate that increases with increased distance from the prompt. This approach yields far fewer image tokens than uniform patch tokenization. As a result we can drastically reduce the computational cost of segmentation without reducing model size. Furthermore, the foveation focuses the model on the region of interest, a potentially useful inductive bias. We show that our Segment This Thing model is more efficient than prior work while remaining competitive on segmentation benchmarks. It can easily run at interactive frame rates on consumer hardware and is thus a promising tool for augmented reality or robotics applications.
Parabolic mean curvature flow-driven active contour models (PMCF-ACMs) are widely used in image segmentation, which however depend heavily on the selection of initial curve configurations. In this paper, we firstly propose several hyperbolic mean curvature flow-driven ACMs (HMCF-ACMs), which introduce tunable initial velocity fields, enabling adaptive optimization for diverse segmentation scenarios. We shall prove that HMCF-ACMs are indeed normal flows and establish the numerical equivalence between dissipative HMCF formulations and certain wave equations using the level set method with signed distance function. Building on this framework, we furthermore develop hyperbolic dual-mode regularized flow-driven ACMs (HDRF-ACMs), which utilize smooth Heaviside functions for edge-aware force modulation to suppress over-diffusion near weak boundaries. Then, we optimize a weighted fourth-order Runge-Kutta algorithm with nine-point stencil spatial discretization when solving the above-mentioned wave equations. Experiments show that both HMCF-ACMs and HDRF-ACMs could achieve more precise segmentations with superior noise resistance and numerical stability due to task-adaptive configurations of initial velocities and initial contours.
This paper presents a solution for multi source localization using only angle of arrival measurements. The receiver platform is in motion, while the sources are assumed to be stationary. Although numerous methods exist for single source localization, many relying on pseudo-linear formulations or non convex optimization techniques, there remains a significant gap in research addressing multi source localization in dynamic environments. To bridge this gap, we propose a deep learning-based framework that leverages semantic segmentation models for multi source localization. Specifically, we employ UNet and UNetPP as backbone models, processing input images that encode the platform's positions along with the corresponding direction finding lines at each position. By analyzing the intersections of these lines, the models effectively identify and localize multiple sources. Through simulations, we evaluate both single- and multi-source localization scenarios. Our results demonstrate that while the proposed approach performs comparably to traditional methods in single source localization, it achieves accurate source localization even in challenging conditions with high noise levels and an increased number of sources.
We present SA-Radar (Simulate Any Radar), a radar simulation approach that enables controllable and efficient generation of radar cubes conditioned on customizable radar attributes. Unlike prior generative or physics-based simulators, SA-Radar integrates both paradigms through a waveform-parameterized attribute embedding. We design ICFAR-Net, a 3D U-Net conditioned on radar attributes encoded via waveform parameters, which captures signal variations induced by different radar configurations. This formulation bypasses the need for detailed radar hardware specifications and allows efficient simulation of range-azimuth-Doppler (RAD) tensors across diverse sensor settings. We further construct a mixed real-simulated dataset with attribute annotations to robustly train the network. Extensive evaluations on multiple downstream tasks-including 2D/3D object detection and radar semantic segmentation-demonstrate that SA-Radar's simulated data is both realistic and effective, consistently improving model performance when used standalone or in combination with real data. Our framework also supports simulation in novel sensor viewpoints and edited scenes, showcasing its potential as a general-purpose radar data engine for autonomous driving applications. Code and additional materials are available at https://zhuxing0.github.io/projects/SA-Radar.
Segmenting Synthetic Aperture Radar (SAR) images is crucial for many remote sensing applications, particularly water body detection. However, deep learning-based segmentation models often face challenges related to convergence speed and stability, mainly due to the complex statistical distribution of this type of data. In this study, we evaluate the impact of mode normalization on two widely used semantic segmentation models, U-Net and SegNet. Specifically, we integrate mode normalization, to reduce convergence time while maintaining the performance of the baseline models. Experimental results demonstrate that mode normalization significantly accelerates convergence. Furthermore, cross-validation results indicate that normalized models exhibit increased stability in different zones. These findings highlight the effectiveness of normalization in improving computational efficiency and generalization in SAR image segmentation.
Over the past decade, Medical Image Segmentation (MIS) using Deep Neural Networks (DNNs) has achieved significant performance improvements and holds great promise for future developments. This paper presents a comprehensive study on MIS based on DNNs. Intelligent Vision Systems are often evaluated based on their output levels, such as Data, Information, Knowledge, Intelligence, and Wisdom (DIKIW),and the state-of-the-art solutions in MIS at these levels are the focus of research. Additionally, Explainable Artificial Intelligence (XAI) has become an important research direction, as it aims to uncover the "black box" nature of previous DNN architectures to meet the requirements of transparency and ethics. The study emphasizes the importance of MIS in disease diagnosis and early detection, particularly for increasing the survival rate of cancer patients through timely diagnosis. XAI and early prediction are considered two important steps in the journey from "intelligence" to "wisdom." Additionally, the paper addresses existing challenges and proposes potential solutions to enhance the efficiency of implementing DNN-based MIS.
Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical Reasoner (HCR), a novel framework that leverages Large Language Models (LLMs) as clinical guardrails for reliable, zero-shot quality assessment. HCR employs a structured, multistage prompting strategy that guides LLMs through a detailed reasoning process, encompassing knowledge recall, visual feature analysis, anatomical inference, and clinical synthesis, to evaluate segmentations. We evaluated HCR on a diverse dataset across six medical imaging tasks. Our results show that HCR, utilizing models like Gemini 2.5 Flash, achieved a classification accuracy of 78.12%, performing comparably to, and in instances exceeding, dedicated vision models such as ResNet50 (72.92% accuracy) that were specifically trained for this task. The HCR framework not only provides accurate quality classifications but also generates interpretable, step-by-step reasoning for its assessments. This work demonstrates the potential of LLMs, when appropriately guided, to serve as sophisticated evaluators, offering a pathway towards more trustworthy and clinically-aligned quality control for AI in medical imaging.
This paper addresses the problem of category-level pose estimation for articulated objects in robotic manipulation tasks. Recent works have shown promising results in estimating part pose and size at the category level. However, these approaches primarily follow a complex multi-stage pipeline that first segments part instances in the point cloud and then estimates the Normalized Part Coordinate Space (NPCS) representation for 6D poses. These approaches suffer from high computational costs and low performance in real-time robotic tasks. To address these limitations, we propose YOEO, a single-stage method that simultaneously outputs instance segmentation and NPCS representations in an end-to-end manner. We use a unified network to generate point-wise semantic labels and centroid offsets, allowing points from the same part instance to vote for the same centroid. We further utilize a clustering algorithm to distinguish points based on their estimated centroid distances. Finally, we first separate the NPCS region of each instance. Then, we align the separated regions with the real point cloud to recover the final pose and size. Experimental results on the GAPart dataset demonstrate the pose estimation capabilities of our proposed single-shot method. We also deploy our synthetically-trained model in a real-world setting, providing real-time visual feedback at 200Hz, enabling a physical Kinova robot to interact with unseen articulated objects. This showcases the utility and effectiveness of our proposed method.
The robust interpretation of 3D environments is crucial for human-robot collaboration (HRC) applications, where safety and operational efficiency are paramount. Semantic segmentation plays a key role in this context by enabling a precise and detailed understanding of the environment. Considering the intense data hunger for real-world industrial annotated data essential for effective semantic segmentation, this paper introduces a pioneering approach in the Sim2Real domain adaptation for semantic segmentation of 3D point cloud data, specifically tailored for HRC. Our focus is on developing a network that robustly transitions from simulated environments to real-world applications, thereby enhancing its practical utility and impact on a safe HRC. In this work, we propose a dual-stream network architecture (FUSION) combining Dynamic Graph Convolutional Neural Networks (DGCNN) and Convolutional Neural Networks (CNN) augmented with residual layers as a Sim2Real domain adaptation algorithm for an industrial environment. The proposed model was evaluated on real-world HRC setups and simulation industrial point clouds, it showed increased state-of-the-art performance, achieving a segmentation accuracy of 97.76%, and superior robustness compared to existing methods.
Open-Vocabulary semantic segmentation (OVSS) and domain generalization in semantic segmentation (DGSS) highlight a subtle complementarity that motivates Open-Vocabulary Domain-Generalized Semantic Segmentation (OV-DGSS). OV-DGSS aims to generate pixel-level masks for unseen categories while maintaining robustness across unseen domains, a critical capability for real-world scenarios such as autonomous driving in adverse conditions. We introduce Vireo, a novel single-stage framework for OV-DGSS that unifies the strengths of OVSS and DGSS for the first time. Vireo builds upon the frozen Visual Foundation Models (VFMs) and incorporates scene geometry via Depth VFMs to extract domain-invariant structural features. To bridge the gap between visual and textual modalities under domain shift, we propose three key components: (1) GeoText Prompts, which align geometric features with language cues and progressively refine VFM encoder representations; (2) Coarse Mask Prior Embedding (CMPE) for enhancing gradient flow for faster convergence and stronger textual influence; and (3) the Domain-Open-Vocabulary Vector Embedding Head (DOV-VEH), which fuses refined structural and semantic features for robust prediction. Comprehensive evaluation on these components demonstrates the effectiveness of our designs. Our proposed Vireo achieves the state-of-the-art performance and surpasses existing methods by a large margin in both domain generalization and open-vocabulary recognition, offering a unified and scalable solution for robust visual understanding in diverse and dynamic environments. Code is available at https://github.com/anonymouse-9c53tp182bvz/Vireo.
Estimating the 6D pose of objects from RGBD data is a fundamental problem in computer vision, with applications in robotics and augmented reality. A key challenge is achieving generalization to novel objects that were not seen during training. Most existing approaches address this by scaling up training on synthetic data tailored to the task, a process that demands substantial computational resources. But is task-specific training really necessary for accurate and efficient 6D pose estimation of novel objects? To answer No!, we introduce FreeZeV2, the second generation of FreeZe: a training-free method that achieves strong generalization to unseen objects by leveraging geometric and vision foundation models pre-trained on unrelated data. FreeZeV2 improves both accuracy and efficiency over FreeZe through three key contributions: (i) a sparse feature extraction strategy that reduces inference-time computation without sacrificing accuracy; (ii) a feature-aware scoring mechanism that improves both pose selection during RANSAC-based 3D registration and the final ranking of pose candidates; and (iii) a modular design that supports ensembles of instance segmentation models, increasing robustness to segmentation masks errors. We evaluate FreeZeV2 on the seven core datasets of the BOP Benchmark, where it establishes a new state-of-the-art in 6D pose estimation of unseen objects. When using the same segmentation masks, FreeZeV2 achieves a remarkable 8x speedup over FreeZe while also improving accuracy by 5%. When using ensembles of segmentation models, FreeZeV2 gains an additional 8% in accuracy while still running 2.5x faster than FreeZe. FreeZeV2 was awarded Best Overall Method at the BOP Challenge 2024.
Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode text-image alignment information through attention maps or loss functions. This information is valuable for various downstream tasks, including segmentation, text-guided image editing, and compositional image generation. However, current methods heavily rely on the assumption of perfect text-image alignment in diffusion models, which is not the case. In this paper, we propose using zero-shot referring image segmentation as a proxy task to evaluate the pixel-level image and class-level text alignment of popular diffusion models. We conduct an in-depth analysis of pixel-text misalignment in diffusion models from the perspective of training data bias. We find that misalignment occurs in images with small sized, occluded, or rare object classes. Therefore, we propose ELBO-T2IAlign, a simple yet effective method to calibrate pixel-text alignment in diffusion models based on the evidence lower bound (ELBO) of likelihood. Our method is training-free and generic, eliminating the need to identify the specific cause of misalignment and works well across various diffusion model architectures. Extensive experiments on commonly used benchmark datasets on image segmentation and generation have verified the effectiveness of our proposed calibration approach.
Cell instance segmentation is critical to analyzing biomedical images, yet accurately distinguishing tightly touching cells remains a persistent challenge. Existing instance segmentation frameworks, including detection-based, contour-based, and distance mapping-based approaches, have made significant progress, but balancing model performance with computational efficiency remains an open problem. In this paper, we propose a novel cell instance segmentation method inspired by the four-color theorem. By conceptualizing cells as countries and tissues as oceans, we introduce a four-color encoding scheme that ensures adjacent instances receive distinct labels. This reformulation transforms instance segmentation into a constrained semantic segmentation problem with only four predicted classes, substantially simplifying the instance differentiation process. To solve the training instability caused by the non-uniqueness of four-color encoding, we design an asymptotic training strategy and encoding transformation method. Extensive experiments on various modes demonstrate our approach achieves state-of-the-art performance. The code is available at https://github.com/zhangye-zoe/FCIS.
Domain Adaptation (DA) is crucial for robust deployment of medical image segmentation models when applied to new clinical centers with significant domain shifts. Source-Free Domain Adaptation (SFDA) is appealing as it can deal with privacy concerns and access constraints on source-domain data during adaptation to target-domain data. However, SFDA faces challenges such as insufficient supervision in the target domain with unlabeled images. In this work, we propose a Segment Anything Model (SAM)-guided Reliable Pseudo-Labels method for SFDA (SRPL-SFDA) with three key components: 1) Test-Time Tri-branch Intensity Enhancement (T3IE) that not only improves quality of raw pseudo-labels in the target domain, but also leads to SAM-compatible inputs with three channels to better leverage SAM's zero-shot inference ability for refining the pseudo-labels; 2) A reliable pseudo-label selection module that rejects low-quality pseudo-labels based on Consistency of Multiple SAM Outputs (CMSO) under input perturbations with T3IE; and 3) A reliability-aware training procedure in the unlabeled target domain where reliable pseudo-labels are used for supervision and unreliable parts are regularized by entropy minimization. Experiments conducted on two multi-domain medical image segmentation datasets for fetal brain and the prostate respectively demonstrate that: 1) SRPL-SFDA effectively enhances pseudo-label quality in the unlabeled target domain, and improves SFDA performance by leveraging the reliability-aware training; 2) SRPL-SFDA outperformed state-of-the-art SFDA methods, and its performance is close to that of supervised training in the target domain. The code of this work is available online: https://github.com/HiLab-git/SRPL-SFDA.