Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· 0 citations· 3 references
Abstract
Abstract. Structure-from-Motion (SfM) pipelines rely heavily on the detection and matching of repeatable keypoints across images, yet the performance of modern learned feature extractors in challenging environments remains insufficiently understood. This paper evaluates classical and deep keypoint detectors for SfM reconstruction using winter Arctic UAV imagery, a domain characterized by low texture, repetitive patterns, and limited man-made structure. We compare three feature pipelines within a shared PyCOLMAP-based framework: SIFT with nearest-neighbor matching (SIFT+NN), SuperPoint, and DISK, along with a hybrid approach combining SuperPoint and DISK correspondences. Quantitative evaluation is conducted using standard SfM metrics, including number of observations, track length, observations per image, and reprojection error, complemented by qualitative analysis of keypoint distributions and reconstruction interpretability. Results show that SIFT+NN consistently achieves the most complete and stable reconstructions, producing the highest number of matched observations and lowest reprojection error across aggregate experiments. However, on more challenging subsets lacking clear structural features, learned methods demonstrate improved robustness, successfully reconstructing multiple views where SIFT fails. SuperPoint provides broader spatial coverage, while DISK produces denser clusters in high-confidence regions, highlighting complementary behaviors between learned approaches. Overall, the findings indicate that classical methods remain strong baselines for Arctic UAV photogrammetry under standard SfM pipelines, while learned detectors offer advantages in difficult conditions. The observed performance gap is attributed to domain mismatch and backend optimization for handcrafted features. These results suggest that domain-specific training and improved spatial feature distribution are promising directions for advancing learned keypoint methods in Arctic reconstruction tasks.
Robust image-to-image correspondence is a fundamental challenge for camera-based Visual Simultaneous Localization and Mapping (SLAM). Conventional approaches primarily rely on isolated local feature matching or optical flow prediction, which often suffer from limited robustness under large parallax, high computational overhead, and cumulative drift errors during long-sequence tracking. To address these limitations, we propose SPTNet (SuperPoint Tracking Network), an efficient multi-task neural network that tightly couples feature detection, description, and dense optical flow prediction within a unified architecture. The fundamental innovation of SPTNet is a Hybrid Tracking Module (HTM) governed by a novel Predictor-Corrector mechanism. Specifically, the dense optical flow field acts as a temporal prior to constrain the descriptor matching search space, while the descriptors act as a correction signal, eliminating flow-induced drift at each frame through spatially constrained Sinkhorn optimization. This synergy enables efficient feature reuse via a shared backbone, minimizing redundant computation. Comprehensive experiments on indoor and outdoor datasets demonstrate that SPTNet attains a false matching rate as low as 1.8% at a 5-pixel threshold on HPatches, substantially reduces cumulative drift on long-sequence SLAM benchmarks, and maintains a high execution speed of 35 FPS on standard GPUs, demonstrating a highly compact footprint advantageous for prospective embedded robotic deployment.
Min Pang, Jichao Jiao, Yingjian Zhang· Italian National Conference...· 0 citations
Abstract. Improved availability and quality of high-resolution satellite imagery allow for reliable airplane detection. Yet, fine-grained classification, especially of commercial airliners, remains a formidable challenge. Besides common difficulties, such as varying image artifacts and occlusions, the main challenge lies in the strong visual similarity between airliner families. This paper presents a geometry-aware classification that enhances oriented object detectors by integrating absolute measures and geometric features – fuselage length, wingspan, wing sweep angle, engine count, and fuselage width – in the form of priors into a Bayesian maximum a posteriori (MAP) estimation. The proposed pipeline is detector-agnostic by updating class posteriors without retraining the main detector. On the Gaofen Challenge dataset, it results in consistent improvements based on untuned baseline detectors, which out-perform the top scores of the sophisticated fine-tuned models. An oracle experiment reveals the potential of the approach with an upper limit of the overall mean Average Precision of up to 0.96 and 0.98 for Gaofen and SuperView data, respectively. Furthermore, the impact of the employed geometric attributes is quantitatively evaluated.
Tobias Traiser, Hai Huang, Helmut Mayer· ISPRS Annals of the Photogra...· 0 citations
Abstract. Satellite imagery offers a distinct advantage in Earth observation by providing expansive coverage and enabling the monitoring of inaccessible regions without physical on-site intervention, serving as a significantly more cost-effective and scalable alternative to traditional aerial or ground-based surveys. The task of 3D reconstruction from multi-view satellite images has therefore been a pivotal point of research at the intersection of photogrammetry and remote sensing. Recently, novel-view synthesis techniques such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have accelerated the accuracy and speed of topographic modeling. Among these, Earth Observation Gaussian Splatting (EOGS) has emerged as a state-of-the-art approach by adapting 3DGS to handle the unique geometric and radiometric characteristics of satellite data, including Rational Polynomial Coefficients (RPCs) and varying solar conditions. However, the standard EOGS pipeline relies on stochastic initialization, where Gaussians are distributed uniformly within a volumetric bounding box, leading to high computational overhead and dependency on aggressive pruning that can inadvertently remove critical geometric features, particularly in areas with complex urban structures. To address these limitations, we propose Bundle-Adjusted Initialization for Earth Observation Gaussian Splatting, which leverages sparse point clouds from bundle adjustment as geometric priors for Gaussian initialization. Combined with an adaptive densification strategy, our method achieves faster convergence and improved DSM accuracy on the DFC2019 dataset compared to the EOGS baseline.
Jiyong Kim, Shuang Song, Rongjun Qin· The International Archives o...· 0 citations
Small-object detection in unmanned aerial vehicle (UAV) imagery is challenging because targets are often tiny, densely distributed, and embedded in cluttered backgrounds, while edge platforms impose strict computational constraints. This paper presents a lightweight end-to-end detector based on RT-DETR to improve detection accuracy, localisation quality, and deployment efficiency. The proposed method includes three components: a detail-enhanced backbone for preserving fine-grained texture and edge cues, rotary positional encoding combined with a content-aware bidirectional feature pyramid for improved cross-scale alignment, and a difficulty-aware composite regression loss for more stable bounding-box optimisation. Experiments on VisDrone2019 and DOTA show that the proposed method improves mAP50 by 3.5% and 1.6%, respectively, over the RT-DETR baseline, while reducing the number of parameters by 28.6%. Ablation studies confirm the complementary contributions of the three components, and robustness experiments demonstrate reliable performance under challenging aerial conditions. Deployment on a Jetson Orin NX using a self-built UAV dataset further validates the practicality of the method for edge-side UAV monitoring.
Na Liu, Xiaoying Liao, Haotian Song et al.· 2026 IEEE 27th China Confere...· 0 citations
Abstract. Accurate camera pose estimation in urban environments remains challenging when reference imagery is generated from low-detailed, textureless 3D city models and must be matched against real world imagery. In this work we (i) extend our existing iterative object-basesd visual localization approach with an additional semantic feature and (ii) conduct a systematic baseline study of contemporary feature matching techniques on such cross-domain query-reference image pairs. As a first step to close the domain gap, we augment our iterative object-based visual localization pipeline with semantic masks derived from a pretrained semantic segmentation model. Intersection-over-Union between query and rendered masks is incorporated into the matching score, leading to a better pose accuracy. For the baseline study, we use a range of feature matching techniques: handcrafted (SIFT, AKAZE, ORB, FAST), learned detectors (XFeat, Key.Net, DeDoDe, DISK, AffNet), learned descriptors (XFeat, DISK, DeDoDe, HardNet), learned matchers (LightGlue, LoFTR), the line matcher SOLD2, and the learned matchers MINIMA-RoMa, MINIMA-LoFTR, MINIMA-XoFTR, and MatchAnything, which were trained on cross-modality datasets. The cross-modality focused matchers achieved the best results. For 20% 10%, 9%, and 7% of the evaluated query images the estimated camera pose had a translation error less than 5m and a rotation error less than 5◦. In this context, the other methods were only able to achieve a maximum success rate of 1.4%.
Yasmin Loeper, Markus Gerke, P. Fanta-Jende· The International Archives o...· 0 citations
This work presents the first complete system for automated six degrees of freedom (6DOF) satellite pose estimation from spatially resolved, ground-based, adaptive optics (AO)-corrected imagery, addressing a key challenge in Space Domain Awareness (SDA). The approach mitigates the need for human labeling by directly regressing satellite orientation and position from blurry, noisy, and deeply shadowed imagery. A multi-stage deep neural network pipeline localizes the satellite, predicts pose, and optionally applies temporal filtering. Networks are trained exclusively on fully synthetic imagery generated from a CAD model, yet generalize effectively to real data, bridging the Sim2Real domain gap. On 137 real, human-labeled test images of Seasat, the model achieved a mean rotation error of 5° and a mean image-plane translation error of 21 cm. Slant range error was quantitatively evaluated on synthetic data due to unknown real-sensor parameters. Qualitative evaluation of additional real Seasat imagery rated 177 of 199 predicted poses as “ground truth equivalent” or “high-confidence match,” with zero catastrophic failures. The system was extended to seven degrees of freedom (7DOF) for satellites with articulating components and demonstrated on real Hubble Space Telescope (HST) imagery, achieving 5.5° rotation error, 51 cm image-plane translation error, and 8° symmetry-adjusted solar array error on a 249-frame pass with causal temporal filtering. Across 586 real test images from Seasat and HST (captured over multiple decades under diverse conditions) the system consistently performed well. Full 6DOF performance was quantified on a high-fidelity wave optics (HFWO) synthetic test set of Seasat, where the model achieved 8.4° mean rotation error, 34 cm image-plane translation error, and 1.4% line-of-sight range error at r0=6 cm and 1031 km range. In a limited 200-image benchmark, the model demonstrated 48% lower mean rotation error than a single human labeler while operating ∼800× faster. It required <40 h and a single A100 GPU to generate data and train. The approach was also demonstrated for ARGOS, a smaller satellite with highly symmetric geometry. An exploratory General Image-Quality Equation-based image quality metric (AO-IQ) was introduced as an empirical correlate for pose accuracy. General-purpose models like GPT-4o and Depth Anything V2 failed across most SDA tasks, but rapid gains in vision-language models warrant continued monitoring. These results establish a new operational baseline for practical, real-time satellite pose estimation from AO SDA imagery.
Thomas J. Dickinson, Dawson Friesenhahn, Justin Fletcher et al.· Aerospace· 0 citations