ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"Epistemic and aleatoric uncertainty in optical vegetation trait retrieval: Concepts, Methods, and Outlook","authors":"Jochem Verrelst ,&nbsp;José Luis García-Soria ,&nbsp;Pablo Reyes-Muñoz ,&nbsp;Emma De Clerck ,&nbsp;Miguel Morata ,&nbsp;Juan Pablo Rivera-Caicedo","doi":"10.1016/j.isprsjprs.2026.02.020","DOIUrl":"10.1016/j.isprsjprs.2026.02.020","url":null,"abstract":"<div><div>Remote sensing of vegetation traits, such as leaf area index, chlorophyll content, and canopy nitrogen content, underpins assessments of ecosystem health, crop productivity, and climate impacts. Yet the uncertainty of these retrievals is often under-reported or ambiguously defined. This scoping review clarifies and operationalizes the distinction between aleatoric (sensor- and observation-driven, irreducible) and epistemic (model- and knowledge-driven, reducible) uncertainty, a conceptual framework that is only beginning to gain traction in vegetation-trait mapping. It highlights how both components originate and propagate through the full Earth-observation processing chain, from top-of-atmosphere radiance (L1) to surface reflectance (L2A) and vegetation traits (L2B), and how they can be consistently quantified and combined. We synthesize methodologies to quantify and, where possible, disentangle these contributions: analytical and Monte Carlo propagation for aleatoric error; Gaussian process regression, Bayesian neural networks, ensembles, and quantile-based methods for epistemic uncertainty; and their integration into retrieval frameworks such as hybrid approaches that couple radiative transfer models with machine learning regression algorithms. We further review diagnostics (coverage, scoring rules, reliability diagrams, probability-integral-transform histograms), out-of-distribution detection, and strategies to reduce epistemic uncertainty via active learning, domain adaptation, and improved priors and models. Looking ahead, upcoming optical ESA missions such as S2NG, FLEX, and CHIME place increasing emphasis on traceable uncertainty budgets and are expected to provide either per-pixel L2A uncertainty layers or the metadata required for their derivation. Such information will be critical for propagating measurement-driven (aleatoric) error into L2B trait products and for interpreting total predictive uncertainty, including prediction intervals. We advocate routine release of L2B uncertainty layers (components and totals) with transparent calibration, benchmarking, and interoperable metadata to support data assimilation, operational monitoring, and risk-aware decision-making.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"234 ","pages":"Pages 20-45"},"PeriodicalIF":12.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SP-KAN: Sparse-sine perception Kolmogorov–Arnold networks for infrared small target detection","authors":"Shuai Yuan ,&nbsp;Yu Liu ,&nbsp;Xiaopei Zhang ,&nbsp;Xiang Yan ,&nbsp;Hanlin Qin ,&nbsp;Naveed Akhtar","doi":"10.1016/j.isprsjprs.2026.02.019","DOIUrl":"10.1016/j.isprsjprs.2026.02.019","url":null,"abstract":"<div><div>Infrared small target detection (IRSTD) plays a critical role in diverse complex remote sensing scenarios. However, existing IRSTD methods struggle to discriminate dim targets that are heavily entangled with complex interference due to their fixed activation representations. To tackle this issue, we reformulate IRSTD as a global context modulation problem driven by sparse nonlinear modules and propose a Sparse-sine Perception Kolmogorov–Arnold Network (SP-KAN). It marks a novel attempt to leverage the superior nonlinear capability of the Kolmogorov–Arnold theory for robust IRSTD. Specifically, a compressed vision transformer encoder is first employed to capture long-range spatial dependencies, while the proposed pattern complementarity module (PCM) constructs their essential nonlinear interactions. The PCM unifies channel-wise mappings of tokenized representations with local spatial saliency of structured features, enhancing target–background discrimination via multi-dimensional and multi-intensity nonlinear embedding. Within the PCM, a sparse-sine perception Kolmogorov–Arnold layer (SPKAL) is introduced to perceive the original nonlinear space and a sparse grid-based high-dimensional sinusoidal latent space at the pixel level, enabling fine-grained interactions among neurons and aligning with the inherent sparsity of small targets. Extensive experiments across four datasets demonstrate that SP-KAN consistently surpasses state-of-the-art IRSTD methods in accuracy, robustness, and generalization, verifying its superior capability in sparse nonlinear modeling. Code will be available at the author’s homepage <span><span>https://github.com/xdFai</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"234 ","pages":"Pages 1-19"},"PeriodicalIF":12.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RoofX-Net: A tailored approach to accurate multi-type rooftop segmentation in remote sensing images using edge and scale awareness","authors":"Keyu Chen ,&nbsp;Tianlei Wang ,&nbsp;Zhiyou Yang ,&nbsp;Fan Li ,&nbsp;Ma Luo ,&nbsp;Ruoning Zhang ,&nbsp;Hong Qu ,&nbsp;Wenyu Chen","doi":"10.1016/j.isprsjprs.2026.02.015","DOIUrl":"10.1016/j.isprsjprs.2026.02.015","url":null,"abstract":"<div><div>High-resolution remote-sensing images play a vital role in advancing solar photovoltaic (PV) system deployment, which is crucial for renewable energy generation. Urban rooftops are widely recognized as optimal platforms for PV deployment, and the accurate identification of multi-type rooftops using remote-sensing images is essential for effective PV capacity planning. However, existing image segmentation models face challenges in rooftop segmentation, particularly in addressing ambiguous edges and variations in rooftop scales. To address these challenges, we propose <em>RoofX-Net</em>, a novel decoder within an encoder–decoder framework designed to enhance the precision of rooftop segmentation. RoofX-Net introduces two key modules: (1) the Edge Extraction Module, which employs hand-crafted edge-computing kernels for improved edge detection, and (2) the Scale Awareness Module, which addresses scale variations by generating geometric awareness at different scales, with a specific focus on small-scale rooftops. We conduct a comprehensive evaluation of RoofX-Net on the WHU dataset and our established Rooftop<span><math><msup><mrow></mrow><mrow><mo>+</mo></mrow></msup></math></span> dataset, which is specifically curated to support multi-type rooftop segmentation. RoofX-Net demonstrated superior performance across both datasets. Notably, on the Rooftop<span><math><msup><mrow></mrow><mrow><mo>+</mo></mrow></msup></math></span> dataset, our model achieves an overall accuracy of 96.39%, a mean Intersection over Union (mIoU) of 90.75%, and an F1-score of 95.11%, outperforming the compared models. RoofX-Net is versatile and can be integrated into existing segmentation frameworks, offering enhanced performance with minimal additional cost. In practical urban planning projects, our method significantly reduces planning time while maintaining reliability, demonstrating substantial potential for optimizing solar PV deployment in urban environments. The implementation of the proposed method is publicly available at <span><span>https://github.com/K-Y-Chen/RoofX-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"234 ","pages":"Pages 46-59"},"PeriodicalIF":12.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal remote sensing change detection: An image matching perspective","authors":"Hongruixuan Chen ,&nbsp;Cuiling Lan ,&nbsp;Jian Song ,&nbsp;Damian Ibañez ,&nbsp;Junshi Xia ,&nbsp;Konrad Schindler ,&nbsp;Naoto Yokoya","doi":"10.1016/j.isprsjprs.2026.02.004","DOIUrl":"10.1016/j.isprsjprs.2026.02.004","url":null,"abstract":"<div><div>Change Detection (CD) between images with different modalities is a fundamental capability for remote sensing. In this work, we pinpoint the commonalities between Multimodal Change Detection (MCD) and Multimodal Image Matching (MIM). Accordingly, we present a new unsupervised CD framework designed from the perspective of Image Matching (IM), called IM4CD. It unifies the IM and CD tasks into a single, coherent framework. In this framework, we abandon the prevalent strategy in MCD to compare per-pixel image features, since it is in practice quite difficult to design features that are truly invariant across modalities. Instead, we propose to compute similarity by local template matching and utilize the spatial offset of response peaks to represent change intensity between images with different modalities, and then to integrate it tightly with the co-registration of the two images, which anyway includes such a matching step. In this way, the same off-the-shelf descriptors used for MIM also support MCD. In other words, we first extract modality-independent features, then detect salient points to obtain initial pairs of corresponding Control Points (CP). When matching those points to accurately register the images, CP pairs located in unchanged areas show low residuals, whereas those in changed areas show high residuals. The CPs can then be connected into a Conditional Random Field (CRF), leveraging modality-independent structural relationships to estimate dense change maps. Experimental results show the effectiveness of our method, including robustness to registration errors, its compatibility with different image descriptors, and promising potential for challenging real-world disaster response scenarios.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 487-501"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MMP-Mapper: Multi-modal priors enhancing vectorized HD road map construction from aerial imagery","authors":"Haofeng Xie ,&nbsp;Huiwei Jiang ,&nbsp;Yandi Yang ,&nbsp;Xiangyun Hu","doi":"10.1016/j.isprsjprs.2026.02.008","DOIUrl":"10.1016/j.isprsjprs.2026.02.008","url":null,"abstract":"<div><div>High-definition (HD) road maps are indispensable for autonomous driving, supporting tasks such as localization, planning, and navigation. The traditional construction of HD road maps heavily relies on manual annotation of data from LiDAR, cameras, and GPS/IMU, a process that is both costly and time-consuming. While recent work has explored automatic HD road map extraction from aerial imagery — a data source offering broad-area coverage and superior robustness — existing methods face a critical limitation. They often process only a single, isolated image tile, failing to leverage crucial spatial context and semantic priors from multi-modal data sources. This shortage severely impacts map accuracy and continuity, especially at complex intersections and in occluded areas. To overcome these challenges, we propose MMP-Mapper, a novel framework that enhances HD road map construction with multi-modal priors. MMP-Mapper introduces two key modules: (1) the Contextual Image Fusion (CIF) module, which selects and fuses features from neighbor image tiles to provide spatial continuity; and (2) the Map-Guided Fusion (MGF) module, which uses a Transformer module to fuse the encoded semantic attributes from standard-definition (SD) road maps with geometric priors, guiding HD road map construction. We validate our framework on the Aerial Argoverse 2 and OpenSatMap datasets. Our results demonstrate that MMP-Mapper outperforms state-of-the-art baselines in both accuracy and generalization for aerial-imagery-based HD road map construction.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 543-555"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Satellite-based heat Index estimatioN modEl (SHINE): An integrated machine learning approach for the conterminous United States","authors":"Seyed Babak Haji Seyed Asadollah,&nbsp;Giorgos Mountrakis,&nbsp;Stephen B. Shaw","doi":"10.1016/j.isprsjprs.2026.01.018","DOIUrl":"10.1016/j.isprsjprs.2026.01.018","url":null,"abstract":"<div><div>The accelerating frequency, duration and intensity of extreme heat events demand accurate, spatially complete heat exposure metrics. Here, a modeling approach is presented for estimating the daily-maximum Heat Index (HI) at 1 km spatial resolution. Our study area covered the conterminous United States (CONUS) during the warm season (May to September) between 2003 and 2023. More than 4.6 million observations from approximately 2000 weather stations were paired with weather-related, geographical, land cover and historical climatic factors to develop the proposed Satellite-based Heat Index estimatioN modEl (SHINE). Selected explanatory variables at daily temporal intervals included reanalysis products from Modern-Era Retrospective analysis for Research and Applications (MERRA) and direct satellite products from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor.</div><div>The most influential variables for HI estimation were the MERRA surface layer height and specific humidity products and the dual-pass MODIS daily land surface temperatures. These were followed by land cover products capturing water and forest presence, historical norms of wind speed and maximum temperature, elevation information and the corresponding day of year. An Extreme Gradient Boosting (XGBoost) regressor trained with spatial cross-validation explained 93 % of the variance (R² = 0.93) and attained a Root Mean Square Error (RMSE) of 1.9°C and a Mean Absolute Error (MAE) of 1.4°C. Comparison of alternative configurations showed that while a MERRA-only model provided slightly higher accuracy (RMSE of 1.8°C), its coarse resolution failed to capture fine-scale heat variations. Conversely, a MODIS-only model offered kilometer-scale spatial resolution but with higher estimation errors (RMSE of 2.9°C). Integrating both MERRA and MODIS sources enabled SHINE to maintain spatial detail and preserved accuracy, underscoring the complementary strengths of reanalysis and satellite products. SHINE also demonstrated resistance to missing MODIS LST observations due to clouds as the additional RMSE error was approximately 0.5°C in the worst case of missing both morning and afternoon MODIS land surface temperature observations. Spatial error analysis revealed &lt;1.7°C RMSE in arid and Mediterranean zones but larger, more heterogeneous errors in the humid Midwest and High Plains. From the policy perspective and considering the HI operational range for public-health heat effects, the proposed SHINE approach outperformed typically used proxies, such as land surface and air temperature. The resulting 1 km daily HI estimations can potentially be used as the foundation of the first wall-to-wall, multi-decadal, high resolution heat dataset for CONUS and offer actionable information for public-health heat studies, energy-demand forecasting and environmental-justice implications.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 209-230"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing conditional generative adversarial networks for SAR-to-optical image translation via auxiliary geospatial landscape pattern-augmentation","authors":"Hongbo Liang ,&nbsp;Xuezhi Yang ,&nbsp;Xiangyu Yang ,&nbsp;Xin Jing","doi":"10.1016/j.isprsjprs.2026.01.043","DOIUrl":"10.1016/j.isprsjprs.2026.01.043","url":null,"abstract":"<div><div>Synthetic aperture radar (SAR) enables all-weather, all-day Earth observation, yet speckle noise and geometric distortions from complex electromagnetic scattering imaging severely limit its visual interpretability. SAR-to-optical image translation (S2OIT) has emerged to mitigate these challenges, but remains hindered by the data heterogeneity and spectral discrepancies between SAR and optical domains, where integrating auxiliary knowledge offers a viable remedy. What is more, previous studies rely on a pixel-wise constrained adversarial learning paradigm with limited mining of geospatial landscape information are prone to generating low-fidelity images. To tackle these issues, we propose AGPA-CGAN, a conditional generative adversarial network (CGAN) framework with auxiliary geospatial landscape pattern-augmentation for high-quality S2OIT. AGPA-CGAN progressively narrows the gap between translated and reference images by integrating ample SAR prior properties and geospatial structural information from scenario image pairs into the S2OIT process. Specifically, to fully exploit the tremendous priors of SAR images, we design an auxiliary pseudo-scattering pattern integration (APSPI) module to extract hierarchical subspace frequency conditional representations, thereby aiding AGPA-CGAN in capturing more descriptive cues for S2OIT. In particular, we introduce an unsupervised subspace embedding clustering (SEC) algorithm based on subspace frequency analysis (SSFA) within APSPI to derive statistical pseudo-scattering behavior maps against SAR feature spectrums. Furthermore, to stabilize the integration of SAR priors, we propose a geospatial landscape domain alignment (Geo-LDA) module that applies multi-perspective consistency regularization to align structural correspondences between SAR and optical features. Extensive experiments on three challenging benchmarks demonstrate that AGPA-CGAN surpasses state-of-the-art (SOTA) methods in both translation fidelity and structural realism.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 502-518"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WHU-STree: A multi-modal benchmark dataset for street tree inventory","authors":"Ruifei Ding ,&nbsp;Zhe Chen ,&nbsp;Wen Fan ,&nbsp;Chen Long ,&nbsp;Huijuan Xiao ,&nbsp;Yelu Zeng ,&nbsp;Zhen Dong ,&nbsp;Bisheng Yang","doi":"10.1016/j.isprsjprs.2026.02.011","DOIUrl":"10.1016/j.isprsjprs.2026.02.011","url":null,"abstract":"<div><div>Street trees are vital to urban livability, providing ecological and social benefits. Establishing a detailed, accurate, and dynamically updated street tree inventory has become essential for optimizing these multifunctional assets within space-constrained urban environments. Given that traditional field surveys are time-consuming and labor-intensive, automated surveys utilizing Mobile Mapping Systems (MMS) offer a more efficient solution. However, existing MMS-acquired tree datasets are limited by small-scale scene, limited annotation, or single modality, restricting their utility for comprehensive analysis. To address these limitations, we introduce WHU-STree, a cross-city, richly annotated, and multi-modal urban street tree dataset. Collected across two distinct cities, WHU-STree integrates synchronized point clouds and high-resolution images, encompassing 21,007 annotated tree instances across 50 species and 2 morphological parameters. Leveraging the unique characteristics, WHU-STree concurrently supports over 10 tasks related to street tree inventory. We benchmark representative baselines for two key tasks—tree species classification and individual tree segmentation—based on 18 major species and an “Others” category. Extensive experiments demonstrate that while multi-modal fusion yields improvements over uni-modal baselines, it currently presents performance gaps compared to strong 3D-only methods, indicating that effective fusion remains a challenging open problem requiring further research. In particular, we identify key challenges and outline potential future works for fully exploiting WHU-STree, encompassing multi-modal fusion, multi-task collaboration, cross-domain generalization, spatial pattern learning, and Multi-modal Large Language Model for street tree asset management. The WHU-STree dataset is accessible at: <span><span>https://github.com/WHU-USI3DV/WHU-STree</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 519-542"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EAV-DETR: Efficient Arbitrary-View oriented object detection with probabilistic guarantees for UAV imagery","authors":"Haoyu Zuo ,&nbsp;Minghao Ning ,&nbsp;Yiming Shu ,&nbsp;Shucheng Huang ,&nbsp;Chen Sun","doi":"10.1016/j.isprsjprs.2026.02.009","DOIUrl":"10.1016/j.isprsjprs.2026.02.009","url":null,"abstract":"<div><div>Oriented object detection is critical for enhancing the visual perception of unmanned aerial vehicles (UAVs). However, existing detectors primarily designed for general aerial imagery often struggle to address the unique challenges of UAV imagery, including substantial scale variations, dense clustering, and arbitrary orientations. Furthermore, these models lack probabilistic guarantees required for safety-critical applications. To address these challenges, we propose EAV-DETR, an efficient oriented object detection transformer designed for UAV imagery. Specifically, we first propose a novel scale-adaptive center supervision (SACS) strategy that explicitly enhances the encoder’s feature representations by imposing pixel-level localization constraints with zero inference overhead. Second, we design an anisotropic decoupled rotational attention (ADRA) module, which achieves superior feature alignment for objects of arbitrary morphology by generating a non-rigid adaptive sampling field. Finally, we propose a pose-aware Mondrian conformal prediction (PA-MCP) method, which utilizes the UAV’s flight pose as a physical prior to generate prediction sets with conditional coverage guarantees, thereby providing reliable uncertainty quantification. Extensive experiments on multiple aerial imagery datasets validate the effectiveness of our model. Compared to previous state-of-the-art methods, EAV-DETR improves <span><math><msub><mrow><mtext>AP</mtext></mrow><mrow><mn>75</mn></mrow></msub></math></span> on CODrone by 1.76% while achieving a 52% faster inference speed (46.38 vs 30.55 FPS), and improves <span><math><msub><mrow><mtext>AP</mtext></mrow><mrow><mn>50</mn><mo>:</mo><mn>95</mn></mrow></msub></math></span> on UAV-ROD by 3.17%. Our code is available at <span><span>https://github.com/zzzhak/EAV-DETR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 575-587"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RegScorer: Learning to select the best transformation of point cloud registration","authors":"Xiaochen Yang ,&nbsp;Haiping Wang ,&nbsp;Yuan Liu ,&nbsp;Bisheng Yang ,&nbsp;Zhen Dong","doi":"10.1016/j.isprsjprs.2026.01.034","DOIUrl":"10.1016/j.isprsjprs.2026.01.034","url":null,"abstract":"<div><div>We propose RegScorer, a model learning to identify the optimal transformation to register unaligned point clouds. Existing registration advancements can generate a set of candidate transformations, which are then evaluated using conventional metrics such as Inlier Ratio (IR), Mean Squared Error (MSE) or Chamfer Distance (CD). The candidate achieving the best score is selected as the final result. However, we argue that these metrics often fail to select the correct transformation, especially in challenging scenarios involving symmetric objects, repetitive structures, or low-overlap regions. This leads to significant degradation in registration performance, a problem that has long been overlooked. The core issue lies in their limited focus on local geometric consistency and inability to capture two key conflict cases of misalignment: (1) point pairs that are spatially close after alignment but have conflicting features, and (2) point pairs with high feature similarity but large spatial distances after alignment. To address this, we propose RegScorer, which models both the spatial and feature relationships of all point pairs. This allows RegScorer to learn to capture the above conflict cases and provides a more reliable score for transformation quality. On the 3DLoMatch and ScanNet datasets, RegScorer demonstrate <strong>19.3</strong>% and <strong>14.1</strong>% improvements in registration recall, leading to <strong>4.7</strong>% and <strong>5.1</strong>% accuracy gains in multiview registration. Moreover, when generalized to symmetric and low-texture outdoor scenes, RegScorer achieves a <strong>25</strong>% increase in transformation recall over IR metric, highlighting its robustness and generalizability. The pre-trained model and the complete code repository can be accessed at <span><span>https://github.com/WHU-USI3DV/RegScorer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 266-277"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}