2026· IEEE Geoscience and Remote Sensing Letters· Vol 23, pp. 2506005-2506005· 0 citations· 15 references
Abstract
High-precision, pixel-level annotations are indispensable for remote sensing semantic segmentation and related tasks, yet producing such labels manually is prohibitively expensive. Although recent generative models can synthesize realistic remote sensing data, existing approaches typically either rely heavily on preexisting ground-truth masks as conditioning inputs or lack precise control over the spatial layout of the generated content. To address this gap, we propose Graph2Scene, a novel framework for the joint generation of remote sensing images and pixel-level labels driven by scene graphs. This framework establishes a flexible control mechanism that utilizes scene graphs derived from existing semantic labels during training to learn semantic priors, while enabling users to explicitly define object quantities, categories, and topological relationships for customized generation during inference. Graph2Scene adopts a two-stage cascade: Graph2Mask encodes the scene graph into textual prompts and employs an image-level low-rank adaptation (LoRA) to finetune a FLUX model for label generation; Mask2Scene uses a class-level LoRA strategy to learn fine-grained visual features and generates remote sensing images conditioned on the label. Experiments on our developed non-agricultural conversion process (NACP) dataset and the public LoveDA dataset show that Graph2Scene effectively produces structurally coherent and visually realistic remote sensing images together with accurate pixel-level annotations. The code will be made available at https://github.com/GeoRSAI/Graph2Scene
A lightweight and efficient framework that integrates CLIP and DINO foundation models to address three challenges: semantic misalignment between generic text prompts and RSI-specific visuals; static CAM quality; and incomplete object coverage is proposed.
Xin Li, Nicola Genzano, M. Gianinetto et al.· ISPRS Annals of the Photogra...· 0 citations
A three-stage framework that integrates complementary priors from Contrastive Language–Image Pre-training, Self-Distillation with No Labels version 2 (DINOv2), and the Segment Anything Model (SAM) is proposed, demonstrating the effectiveness and generalizability of the proposed framework across diverse remote sensing scenarios under image-level supervision.
Abstract. Zero-shot semantic segmentation (ZSSS) is a crucial task in remote sensing image understanding, yet existing methods still suffer from limited generalization to unseen classes. To address this issue, we propose a Knowledge Graph (KG) enhanced ZSSS framework, which introduces explicit hierarchical and relational information into class embeddings to achieve more structured and semantically consistent representations. Specifically, a KG class encoder is designed, consisting of the class enhanced query (CEQ) and class enhanced embedding (CEE) modules, which extract class-relevant subgraphs from a self-constructing Remote Sensing Semantic Class Knowledge Graph (RSSCKG) and generate knowledge-enriched embeddings through a text encoder. Experiments on three public remote sensing datasets demonstrate that the proposed method consistently improves performance across seven state-of-the-art ZSSS frameworks. The integration of KG-based embeddings yields significant gains in the evaluation metrics, with particularly strong improvements on unseen classes, while maintaining accuracy on seen classes. Compared with enhancement strategies based on large language model (LLM) generated descriptions, the proposed KG class encoder exhibit superior semantic separability and stability. These results validate the effectiveness, generalization, and scalability of the proposed framework for ZSSS in remote sensing imagery.
Wu-da Huang, Huchen Li, Shuai Zhang et al.· ISPRS Annals of the Photogra...· 0 citations
Referring remote sensing image segmentation (RRSIS) aims to segment target ground objects in high-resolution remote sensing imagery according to textual descriptions. Due to complex backgrounds and large-scale variations, accurately aligning linguistic semantics with spatial regions remains a challenging problem. Existing RRSIS methods are predominantly segmentation-centric, where textual descriptions mainly serve as conditional guidance for pixel-wise prediction rather than explicitly enforcing semantic consistency between visual regions and linguistic representations. This limitation often leads to suboptimal fine-grained alignment and insufficient suppression of background-dominant regions. To address these challenges, we propose a novel RRSIS framework centered on structure-constrained semantic contrastive learning (CL), termed S2CLNet. Departing from the segmentation-driven paradigm, instead of relying solely on segmentation supervision, S2CL introduces region-level structural constraints to perform fine-grained CL in the joint embedding space. This design encourages semantically corresponding visual regions and linguistic representations to be more closely aligned while effectively separating target regions from irrelevant background areas. Furthermore, we develop a dynamic modality balancing module (DMBM) to enhance cross-modal interaction under complex remote sensing scenarios. The DMBM jointly models bidirectional cross-modal attention (BCA) and dynamically adjusts the relative contributions of visual and linguistic modalities according to scene complexity and linguistic specificity, thereby facilitating more adaptive and robust multimodal feature integration. Extensive experiments on three public benchmarks, RefSegRS, RRSIS-D, and RISBench, demonstrate that the proposed method achieves superior performance compared with state-of-the-art approaches. The code will be publicly available at https://github.com/45degreesl
Sen Lei, Shuai Li, Xin-Yu Xiao et al.· IEEE Transactions on Geoscie...· 0 citations
Multimodal fusion methods have shown great potential in remote sensing image analysis, but existing approaches rely heavily on massive amounts of annotated data. This is not only costly and time-consuming but also prone to subjective bias. To address this issue, we propose a category-prior-based self-supervised framework, CGSNet, which uses category prior maps extracted from multispectral images as supervisory signals for end-to-end training. An adaptive confidence-weighted pseudo-label generation mechanism is designed to alleviate noise and errors in prior maps by replacing binary labels with continuous confidence maps, enabling the learning of uncertain interclass features. In addition, a multispectral feature-guided refinement strategy utilizes color and texture information to calibrate class transition regions and enhance the discriminative power of pseudo-labels in complex scenes. A dynamic mask selection strategy further enhances the model’s robustness and generalization capabilities through progressive learning. Experiments demonstrate that CGSNet achieves state-of-the-art performance without the need for human annotation, achieving an Mean Intersection over Union (mIoU) score of 78.46% on the Gaofen image dataset (GID) (vegetation) dataset and 79.58% on the Zurich (vegetation) dataset—12.22% and 15.07% higher than existing methods, respectively—while exhibiting strong cross-dataset zero-shot generalization capabilities. The code will be available at https://github.com/NUAALISILab
Jiahang Liu, Jian Cui, Mao-yin Guo et al.· IEEE Transactions on Geoscie...· 0 citations
Remote-sensing systems usually describe urban content with detection boxes, semantic masks, or vector boundaries. Such outputs locate classes and support image-plane scoring, yet they do not by themselves constitute an executable layout that retains object identities, typed relations, topology, and regeneration rules. Code-as-City instead casts urban-layout extraction from a single top-down image as constrained code generation with a multimodal large language model (MLLM). An image model first produces an aligned five-class semantic layout prior. Three ordered MLLM passes use the image and this prior to recover roads, land-cover regions and relations, and buildings. Deterministic normalization converts the accumulated records into a city graph and a restricted layout program. Executing the program creates a renderable 3D city layout and an orthographic semantic projection over shared geometry. The projection admits pixel-level comparison with remote-sensing masks, while named objects, relations, and editing operations remain available for synchronized regeneration of both views. Evaluated on the 100 scenes of CityLayout-100, the complete framework obtains 41.1% mean intersection-over-union and 48.3% global intersection-over-union. This result provides quantitative evidence that visual observations can be translated into inspectable, editable city code with coupled planar and 3D outputs.
Zigan Zhou, Kai Li, Yupeng Deng· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
