Rongjun Qin

Rongjun Qin, Feng Chen, Tonghan Wang et al. · harvard, tsinghua

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning accommodate teams of different sizes, heavily relying on the generalization ability of neural networks for adapting to unseen tasks. We believe that the relationship among tasks provides the key information for policy adaptation. In this paper, we try to discover and exploit common structures among tasks for more efficient transfer, and propose to learn effect-based task representations as a common space of tasks, using an alternatively fixed training scheme. We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks. As a result, the proposed method can help transfer learned cooperation knowledge to new tasks after training on a few source tasks. We also find that fine-tuning the transferred policies help solve tasks that are hard to learn from scratch.

Shengxi Gui, Rongjun Qin, Yang Tang

Deriving LoD2 models from orthophoto and digital surface models (DSM) reconstructed from satellite images is a challenging task. Existing solutions are mostly system approaches that require complicated step-wise processes, including not only heuristic geometric operations, but also high-level steps such as machine learning-based semantic segmentation and building detection. Here in this paper, we describe an open-source tool, called SAT2LOD2, built based on a minorly modified version of our recently published work. SAT2LoD2 is a fully open-source and GUI (Graphics User Interface) based software, coded in Python, which takes an orthophoto and DSM as inputs, and outputs individual building models, and it can additionally take road network shapefiles, and customized classification maps to further improve the reconstruction results. We further improve the robustness of the method by 1) intergrading building segmentation based on HRNetV2 into our software; and 2) having implemented a decision strategy to identify complex buildings and directly generate mesh to avoid erroneous LoD2 reconstruction from a system point of view. The software can process a moderate level of data (around 5000*5000 size of orthophoto and DSM) using a PC with a graphics card supporting CUDA. Furthermore, the GUI is self-contained and stores the intermediate processing results facilitating researchers to learn the process easily and reuse intermediate files as needed. The updated codes and software are available under this GitHub page: https://github.com/GDAOSU/LOD2BuildingModel.

Ningli Xu, Rongjun Qin, Shuang Song

Recent advances in computer vision and deep learning have shown promising performance in estimating rigid/similarity transformation between unregistered point clouds of complex objects and scenes. However, their performances are mostly evaluated using a limited number of datasets from a single sensor (e.g. Kinect or RealSense cameras), lacking a comprehensive overview of their applicability in photogrammetric 3D mapping scenarios. In this work, we provide a comprehensive review of the state-of-the-art (SOTA) point cloud registration methods, where we analyze and evaluate these methods using a diverse set of point cloud data from indoor to satellite sources. The quantitative analysis allows for exploring the strengths, applicability, challenges, and future trends of these methods. In contrast to existing analysis works that introduce point cloud registration as a holistic process, our experimental analysis is based on its inherent two-step process to better comprehend these approaches including feature/keypoint-based initial coarse registration and dense fine registration through cloud-to-cloud (C2C) optimization. More than ten methods, including classic hand-crafted, deep-learning-based feature correspondence, and robust C2C methods were tested. We observed that the success rate of most of the algorithms are fewer than 40% over the datasets we tested and there are still are large margin of improvement upon existing algorithms concerning 3D sparse corresopondence search, and the ability to register point clouds with complex geometry and occlusions. With the evaluated statistics on three datasets, we conclude the best-performing methods for each step and provide our recommendations, and outlook future efforts.

Mostafa Elhashash, Hessah Albanwan, Rongjun Qin

The evolution of mobile mapping systems (MMSs) has gained more attention in the past few decades. MMSs have been widely used to provide valuable assets in different applications. This has been facilitated by the wide availability of low-cost sensors, the advances in computational resources, the maturity of the mapping algorithms, and the need for accurate and on-demand geographic information system (GIS) data and digital maps. Many MMSs combine hybrid sensors to provide a more informative, robust, and stable solution by complementing each other. In this paper, we present a comprehensive review of the modern MMSs by focusing on 1) the types of sensors and platforms, where we discuss their capabilities, limitations, and also provide a comprehensive overview of recent MMS technologies available in the market, 2) highlighting the general workflow to process any MMS data, 3) identifying the different use cases of mobile mapping technology by reviewing some of the common applications, and 4) presenting a discussion on the benefits, challenges, and share our views on the potential research directions.

Hessah Albanwan, Rongjun Qin

Deep learning (DL) stereo matching methods gained great attention in remote sensing satellite datasets. However, most of these existing studies conclude assessments based only on a few/single stereo images lacking a systematic evaluation on how robust DL methods are on satellite stereo images with varying radiometric and geometric configurations. This paper provides an evaluation of four DL stereo matching methods through hundreds of multi-date multi-site satellite stereo pairs with varying geometric configurations, against the traditional well-practiced Census-SGM (Semi-global matching), to comprehensively understand their accuracy, robustness, generalization capabilities, and their practical potential. The DL methods include a learning-based cost metric through convolutional neural networks (MC-CNN) followed by SGM, and three end-to-end (E2E) learning models using Geometry and Context Network (GCNet), Pyramid Stereo Matching Network (PSMNet), and LEAStereo. Our experiments show that E2E algorithms can achieve upper limits of geometric accuracies, while may not generalize well for unseen data. The learning-based cost metric and Census-SGM are rather robust and can consistently achieve acceptable results. All DL algorithms are robust to geometric configurations of stereo pairs and are less sensitive in comparison to the Census-SGM, while learning-based cost metrics can generalize on satellite images when trained on different datasets (airborne or ground-view).

Zhengbang Zhu, Rongjun Qin, Junjie Huang et al.

Recommender systems are expected to be assistants that help human users find relevant information automatically without explicit queries. As recommender systems evolve, increasingly sophisticated learning techniques are applied and have achieved better performance in terms of user engagement metrics such as clicks and browsing time. The increase in the measured performance, however, can have two possible attributions: a better understanding of user preferences, and a more proactive ability to utilize human bounded rationality to seduce user over-consumption. A natural following question is whether current recommendation algorithms are manipulating user preferences. If so, can we measure the manipulation level? In this paper, we present a general framework for benchmarking the degree of manipulations of recommendation algorithms, in both slate recommendation and sequential recommendation scenarios. The framework consists of four stages, initial preference calculation, training data collection, algorithm training and interaction, and metrics calculation that involves two proposed metrics. We benchmark some representative recommendation algorithms in both synthetic and real-world datasets under the proposed framework. We have observed that a high online click-through rate does not necessarily mean a better understanding of user initial preference, but ends in prompting users to choose more documents they initially did not favor. Moreover, we find that the training data have notable impacts on the manipulation degrees, and algorithms with more powerful modeling abilities are more sensitive to such impacts. The experiments also verified the usefulness of the proposed metrics for measuring the degree of manipulations. We advocate that future recommendation algorithm studies should be treated as an optimization problem with constrained user preference manipulations.

Rongjun Qin, Guixiang Zhang, Yang Tang

Recent deep learning-based methods outperform traditional learning methods on remote sensing (RS) semantic segmentation/classification tasks. However, they require large training datasets and are generally known for lack of transferability due to the highly disparate RS image content across different geographical regions. Yet, there is no comprehensive analysis of their transferability, i.e., to which extent a model trained on a source domain can be readily applicable to a target domain. Therefore, in this paper, we aim to investigate the raw transferability of traditional and deep learning (DL) models, as well as the effectiveness of domain adaptation (DA) approaches in enhancing the transferability of the DL models (adapted transferability). By utilizing four highly diverse RS datasets, we train six models with and without three DA approaches to analyze their transferability between these datasets quantitatively. Furthermore, we developed a straightforward method to quantify the transferability of a model using the spectral indices as a medium and have demonstrated its effectiveness in evaluating the model transferability at the target domain when the labels are unavailable. Our experiments yield several generally important yet not well-reported observations regarding the raw and adapted transferability. Moreover, our proposed label-free transferability assessment method is validated to be better than posterior model confidence. The findings can guide the future development of generalized RS learning models. The trained models are released under this link: https://github.com/GDAOSU/Transferability-Remote-Sensing

Mostafa Elhashash, Rongjun Qin

Many practical systems for image-based surface reconstruction employ a stereo/multi-stereo paradigm, due to its ability to scale for large scenes and its ease of implementation for out-of-core operations. In this process, multiple and abundant depth maps from stereo matching must be combined and fused into a single, consistent, and clean point cloud. However, the noises and outliers caused by stereo matching and the heterogenous geometric errors of the poses present a challenge for existing fusion algorithms, since they mostly assume Gaussian errors and predict fused results based on data from local spatial neighborhoods, which may inherit uncertainties from multiple depths resulting in lowered accuracy. In this paper, we propose a novel depth fusion paradigm, that instead of numerically fusing points from multiple depth maps, selects the best depth map per point, and combines them into a single and clean point cloud. This paradigm, called select-and-combine (SAC), is achieved through modeling the point level fusion using local Markov Netlets, a micro-network over point across neighboring views for depth/view selection, followed by a Netlets collapse process for point combination. The Markov Netlets are optimized such that they can inherently leverage spatial consistencies among depth maps of neighboring views, thus they can address errors beyond Gaussian ones. Our experiment results show that our approach outperforms existing depth fusion approaches by increasing the F1 score that considers both accuracy and completeness by 2.07% compared to the best existing method. Finally, our approach generates clearer point clouds that are 18% less redundant while with a higher accuracy before fusion

Debao Huang, Mostafa Elhashash, Rongjun Qin

Structure from motion using uncalibrated multi-camera systems is a challenging task. This paper proposes a bundle adjustment solution that implements a baseline constraint respecting that these cameras are static to each other. We assume these cameras are mounted on a mobile platform, uncalibrated, and coarsely synchronized. To this end, we propose the baseline constraint that is formulated for the scenario in which the cameras have overlapping views. The constraint is incorporated in the bundle adjustment solution to keep the relative motion of different cameras static. Experiments were conducted using video frames of two collocated GoPro cameras mounted on a vehicle with no system calibration. These two cameras were placed capturing overlapping contents. We performed our bundle adjustment using the proposed constraint and then produced 3D dense point clouds. Evaluations were performed by comparing these dense point clouds against LiDAR reference data. We showed that, as compared to traditional bundle adjustment, our proposed method achieved an improvement of 29.38%.

Shuang Song, Rongjun Qin

Recovering surface albedos from photogrammetric images for realistic rendering and synthetic environments can greatly facilitate its downstream applications in VR/AR/MR and digital twins. The textured 3D models from standard photogrammetric pipelines are suboptimal to these applications because these textures are directly derived from images, which intrinsically embedded the spatially and temporally variant environmental lighting information, such as the sun illumination, direction, causing different looks of the surface, making such models less realistic when used in 3D rendering under synthetic lightings. On the other hand, since albedo images are less variable by environmental lighting, it can, in turn, benefit basic photogrammetric processing. In this paper, we attack the problem of albedo recovery for aerial images for the photogrammetric process and demonstrate the benefit of albedo recovery for photogrammetry data processing through enhanced feature matching and dense matching. To this end, we proposed an image formation model with respect to outdoor aerial imagery under natural illumination conditions; we then, derived the inverse model to estimate the albedo by utilizing the typical photogrammetric products as an initial approximation of the geometry. The estimated albedo images are tested in intrinsic image decomposition, relighting, feature matching, and dense matching/point cloud generation results. Both synthetic and real-world experiments have demonstrated that our method outperforms existing methods and can enhance photogrammetric processing.

Mostafa Elhashash, Rongjun Qin

Multi-view stereo (MVS) reconstruction is essential for creating 3D models. The approach involves applying epipolar rectification followed by dense matching for disparity estimation. However, existing approaches face challenges in applying dense matching for images with different viewpoints primarily due to large differences in object scale. In this paper, we propose a spherical model for epipolar rectification to minimize distortions caused by differences in principal rays. We evaluate the proposed approach using two aerial-based datasets consisting of multi-camera head systems. We show through qualitative and quantitative evaluation that the proposed approach performs better than frame-based epipolar correction by enhancing the completeness of point clouds by up to 4.05% while improving the accuracy by up to 10.23% using LiDAR data as ground truth.

Shuang Song, Rongjun Qin

Conflating/stitching 2.5D raster digital surface models (DSM) into a large one has been a running practice in geoscience applications, however, conflating full-3D mesh models, such as those from oblique photogrammetry, is extremely challenging. In this letter, we propose a novel approach to address this challenge by conflating multiple full-3D oblique photogrammetric models into a single, and seamless mesh for high-resolution site modeling. Given two or more individually collected and created photogrammetric meshes, we first propose to create a virtual camera field (with a panoramic field of view) to incubate virtual spaces represented by Truncated Signed Distance Field (TSDF), an implicit volumetric field friendly for linear 3D fusion; then we adaptively leverage the truncated bound of meshes in TSDF to conflate them into a single and accurate full 3D site model. With drone-based 3D meshes, we show that our approach significantly improves upon traditional methods for model conflations, to drive new potentials to create excessively large and accurate full 3D mesh models in support of geoscience and environmental applications.

Hessah Albanwan, Rongjun Qin

Deep learning (DL) methods are widely investigated for stereo image matching tasks due to their reported high accuracies. However, their transferability/generalization capabilities are limited by the instances seen in the training data. With satellite images covering large-scale areas with variances in locations, content, land covers, and spatial patterns, we expect their performances to be impacted. Increasing the number and diversity of training data is always an option, but with the ground-truth disparity being limited in remote sensing due to its high cost, it is almost impossible to obtain the ground-truth for all locations. Knowing that classical stereo matching methods such as Census-based semi-global-matching (SGM) are widely adopted to process different types of stereo data, we therefore, propose a finetuning method that takes advantage of disparity maps derived from SGM on target stereo data. Our proposed method adopts a simple scheme that uses the energy map derived from the SGM algorithm to select high confidence disparity measurements, at the same utilizing the images to limit these selected disparity measurements on texture-rich regions. Our approach aims to investigate the possibility of improving the transferability of current DL methods to unseen target data without having their ground truth as a requirement. To perform a comprehensive study, we select 20 study-sites around the world to cover a variety of complexities and densities. We choose well-established DL methods like geometric and context network (GCNet), pyramid stereo matching network (PSMNet), and LEAStereo for evaluation. Our results indicate an improvement in the transferability of the DL methods across different regions visually and numerically.

Shuang Song, Luca Morelli, Xinyi Wu et al.

A critical step in the digital surface models(DSM) generation is feature matching. Off-track (or multi-date) satellite stereo images, in particular, can challenge the performance of feature matching due to spectral distortions between images, long baseline, and wide intersection angles. Feature matching methods have evolved over the years from handcrafted methods (e.g., SIFT) to learning-based methods (e.g., SuperPoint and SuperGlue). In this paper, we compare the performance of different features, also known as feature extraction and matching methods, applied to satellite imagery. A wide range of stereo pairs(~500) covering two separate study sites are used. SIFT, as a widely used classic feature extraction and matching algorithm, is compared with seven deep-learning matching methods: SuperGlue, LightGlue, LoFTR, ASpanFormer, DKM, GIM-LightGlue, and GIM-DKM. Results demonstrate that traditional matching methods are still competitive in this age of deep learning, although for particular scenarios learning-based methods are very promising.

Dongli Wu, Zhuoxiao Li, Tongyan Hua et al.

Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions are repeatedly observed, while facades, distant buildings, and occluded structures receive little multi-view support. Existing feed-forward 3D Gaussian Splatting methods directly regress a deterministic representation from sparse inputs, but this often leads to ghosting, melted facades, and stretched textures. Recent pseudo-view and video-based generative reconstruction methods use additional supervision or generative priors. However, they often lack a clear separation between observed geometry and prior-driven content, which can lead to plausible but inconsistent structures. We propose AnyCity, an observation-grounded generative reconstruction framework for sparse aerial urban scenes. AnyCity first predicts an observation-supported geometry latent to anchor reliable structures, and then uses scaffold-conditioned aerial completion tokens to predict a gated residual update for weakly constrained content before Gaussian decoding. During training, dense-to-sparse distillation transfers structural cues from dense-view reconstruction, while an aerial-adapted video diffusion prior provides fine-grained urban appearance cues through gated token conditioning. Observation-preserving objectives keep the refined representation consistent with input-supported geometry. At inference time, AnyCity reconstructs the final 3D Gaussian scene from sparse aerial views in a single feed-forward pass, achieving coherent urban novel-view synthesis with second-level inference. Experiments on synthetic, aerial-domain, UAV-textured, and real-world scenes show consistent improvements over feed-forward baselines.

Deyan Deng, Rongjun Qin

3D Gaussian Splatting (3DGS) has revolutionized real-time rendering with its state-of-the-art novel view synthesis, but its utility for accurate geometric measurement remains underutilized. Compared to multi-view stereo (MVS) point clouds or meshes, 3DGS rendered views present superior visual quality and completeness. However, current point measurement methods still rely on demanding stereoscopic workstations or direct picking on often-incomplete and inaccurate 3D meshes. As a novel view synthesizer, 3DGS renders exact source views and smoothly interpolates in-between views. This allows users to intuitively pick congruent points across different views while operating 3DGS models. By triangulating these congruent points, one can precisely generate 3D point measurements. This approach mimics traditional stereoscopic measurement but is significantly less demanding: it requires neither a stereo workstation nor specialized operator stereoscopic capability. Furthermore, it enables multi-view intersection (more than two views) for higher measurement accuracy. We implemented a web-based application to demonstrate this proof-of-concept (PoC). Using several UAV aerial datasets, we show this PoC allows users to successfully perform highly accurate point measurements, achieving accuracy matching or exceeding traditional stereoscopic methods on standard hardware. Specifically, our approach significantly outperforms direct mesh-based measurements. Quantitatively, our method achieves RMSEs in the 1-2 cm range on well-defined points. More critically, on challenging thin structures where mesh-based RMSE was 0.062 m, our method achieved 0.037 m. On sharp corners poorly reconstructed in the mesh, our method successfully measured all points with a 0.013 m RMSE, whereas the mesh method failed entirely. Code is available at: https://github.com/GDAOSU/3dgs_measurement_tool.

Ningli Xu, Rongjun Qin

Predicting realistic ground views from satellite imagery in urban scenes is a challenging task due to the significant view gaps between satellite and ground-view images. We propose a novel pipeline to tackle this challenge, by generating geospecifc views that maximally respect the weak geometry and texture from multi-view satellite images. Different from existing approaches that hallucinate images from cues such as partial semantics or geometry from overhead satellite images, our method directly predicts ground-view images at geolocation by using a comprehensive set of information from the satellite image, resulting in ground-level images with a resolution boost at a factor of ten or more. We leverage a novel building refinement method to reduce geometric distortions in satellite data at ground level, which ensures the creation of accurate conditions for view synthesis using diffusion networks. Moreover, we proposed a novel geospecific prior, which prompts distribution learning of diffusion models to respect image samples that are closer to the geolocation of the predicted images. We demonstrate our pipeline is the first to generate close-to-real and geospecific ground views merely based on satellite images.

Shuang Song, Rongjun Qin

Modeling outdoor scenes for the synthetic 3D environment requires the recovery of reflectance/albedo information from raw images, which is an ill-posed problem due to the complicated unmodeled physics in this process (e.g., indirect lighting, volume scattering, specular reflection). The problem remains unsolved in a practical context. The recovered albedo can facilitate model relighting and shading, which can further enhance the realism of rendered models and the applications of digital twins. Typically, photogrammetric 3D models simply take the source images as texture materials, which inherently embed unwanted lighting artifacts (at the time of capture) into the texture. Therefore, these polluted textures are suboptimal for a synthetic environment to enable realistic rendering. In addition, these embedded environmental lightings further bring challenges to photo-consistencies across different images that cause image-matching uncertainties. This paper presents a general image formation model for albedo recovery from typical aerial photogrammetric images under natural illuminations and derives the inverse model to resolve the albedo information through inverse rendering intrinsic image decomposition. Our approach builds on the fact that both the sun illumination and scene geometry are estimable in aerial photogrammetry, thus they can provide direct inputs for this ill-posed problem. This physics-based approach does not require additional input other than data acquired through the typical drone-based photogrammetric collection and was shown to favorably outperform existing approaches. We also demonstrate that the recovered albedo image can in turn improve typical image processing tasks in photogrammetry such as feature and dense matching, edge, and line extraction.

Ningli Xu, Rongjun Qin, Debao Huang et al.

Neural Radiance Fields (NeRF) offer the potential to benefit 3D reconstruction tasks, including aerial photogrammetry. However, the scalability and accuracy of the inferred geometry are not well-documented for large-scale aerial assets,since such datasets usually result in very high memory consumption and slow convergence.. In this paper, we aim to scale the NeRF on large-scael aerial datasets and provide a thorough geometry assessment of NeRF. Specifically, we introduce a location-specific sampling technique as well as a multi-camera tiling (MCT) strategy to reduce memory consumption during image loading for RAM, representation training for GPU memory, and increase the convergence rate within tiles. MCT decomposes a large-frame image into multiple tiled images with different camera models, allowing these small-frame images to be fed into the training process as needed for specific locations without a loss of accuracy. We implement our method on a representative approach, Mip-NeRF, and compare its geometry performance with threephotgrammetric MVS pipelines on two typical aerial datasets against LiDAR reference data. Both qualitative and quantitative results suggest that the proposed NeRF approach produces better completeness and object details than traditional approaches, although as of now, it still falls short in terms of accuracy.

Zhiyuan Gao, Wenbin Teng, Gonglin Chen et al.

Integrating aerial imagery-based scene generation into applications like autonomous driving and gaming enhances realism in 3D environments, but challenges remain in creating detailed content for occluded areas and ensuring real-time, consistent rendering. In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience. More specifically, we combine a 3D representation with a view consistent generation model, which ensures coherence between generated images. This method allows for the creation of geometrically consistent ground view images, even with large view gaps. The images maintain improved spatial-temporal coherence and realism, enhancing scene comprehension and visualization from aerial perspectives. To the best of our knowledge, there are no publicly available datasets that contain pairwise geo-aligned aerial and ground view imagery. Therefore, we build a large, synthetic, and geo-aligned dataset using Unreal Engine. Both qualitative and quantitative analyses on this synthetic dataset display superior results compared to other leading synthesis approaches. See the project page for more results: https://chaoren2357.github.io/website-skyeyes/.

Debao Huang, Rongjun Qin

Nowadays, photogrammetrically derived point clouds are widely used in many civilian applications due to their low cost and flexibility in acquisition. Typically, photogrammetric point clouds are assessed through reference data such as LiDAR point clouds. However, when reference data are not available, the assessment of photogrammetric point clouds may be challenging. Since these point clouds are algorithmically derived, their accuracies and precisions are highly varying with the camera networks, scene complexity, and dense image matching (DIM) algorithms, and there is no standard error metric to determine per-point errors. The theory of internal reliability of camera networks has been well studied through first-order error estimation of Bundle Adjustment (BA), which is used to understand the errors of 3D points assuming known measurement errors. However, the measurement errors of the DIM algorithms are intricate to an extent that every single point may have its error function determined by factors such as pixel intensity, texture entropy, and surface smoothness. Despite the complexity, there exist a few common metrics that may aid the process of estimating the posterior reliability of the derived points, especially in a multi-view stereo (MVS) setup when redundancies are present. In this paper, by using an aerial oblique photogrammetric block with LiDAR reference data, we analyze several internal matching metrics within a common MVS framework, including statistics in ray convergence, intersection angles, DIM energy, etc.

Gonglin Chen, Jinsen Wu, Haiwei Chen et al.

Establishing consistent and dense correspondences across multiple images is crucial for Structure from Motion (SfM) systems. Significant view changes, such as air-to-ground with very sparse view overlap, pose an even greater challenge to the correspondence solvers. We present a novel optimization-based approach that significantly enhances existing feature matching methods by introducing geometry cues in addition to color cues. This helps fill gaps when there is less overlap in large-scale scenarios. Our method formulates geometric verification as an optimization problem, guiding feature matching within detector-free methods and using sparse correspondences from detector-based methods as anchor points. By enforcing geometric constraints via the Sampson Distance, our approach ensures that the denser correspondences from detector-free methods are geometrically consistent and more accurate. This hybrid strategy significantly improves correspondence density and accuracy, mitigates multi-view inconsistencies, and leads to notable advancements in camera pose accuracy and point cloud density. It outperforms state-of-the-art feature matching methods on benchmark datasets and enables feature matching in challenging extreme large-scale settings.

Hanyang Liu, Rongjun Qin

Recent advances in 4D scene reconstruction have significantly improved dynamic modeling across various domains. However, existing approaches remain limited under aerial conditions with single-view capture, wide spatial range, and dynamic objects of limited spatial footprint and large motion disparity. These challenges cause severe depth ambiguity and unstable motion estimation, making monocular aerial reconstruction inherently ill-posed. To this end, we present AeroDGS, a physics-guided 4D Gaussian splatting framework for monocular UAV videos. AeroDGS introduces a Monocular Geometry Lifting module that reconstructs reliable static and dynamic geometry from a single aerial sequence, providing a robust basis for dynamic estimation. To further resolve monocular ambiguity, we propose a Physics-Guided Optimization module that incorporates differentiable ground-support, upright-stability, and trajectory-smoothness priors, transforming ambiguous image cues into physically consistent motion. The framework jointly refines static backgrounds and dynamic entities with stable geometry and coherent temporal evolution. We additionally build a real-world UAV dataset that spans various altitudes and motion conditions to evaluate dynamic aerial reconstruction. Experiments on synthetic and real UAV scenes demonstrate that AeroDGS outperforms state-of-the-art methods, achieving superior reconstruction fidelity in dynamic aerial environments.

Ningli Xu, Rongjun Qin

Cross-view localization and synthesis are two fundamental tasks in cross-view visual understanding, which deals with cross-view datasets: overhead (satellite or aerial) and ground-level imagery. These tasks have gained increasing attention due to their broad applications in autonomous navigation, urban planning, and augmented reality. Cross-view localization aims to estimate the geographic position of ground-level images based on information provided by overhead imagery while cross-view synthesis seeks to generate ground-level images based on information from the overhead imagery. Both tasks remain challenging due to significant differences in viewing perspective, resolution, and occlusion, which are widely embedded in cross-view datasets. Recent years have witnessed rapid progress driven by the availability of large-scale datasets and novel approaches. Typically, cross-view localization is formulated as an image retrieval problem where ground-level features are matched with tiled overhead images feature, extracted by convolutional neural networks (CNNs) or vision transformers (ViTs) for cross-view feature embedding. Cross-view synthesis, on the other hand, seeks to generate ground-level views based on information from overhead imagery, generally using generative adversarial networks (GANs) or diffusion models. This paper presents a comprehensive survey of advances in cross-view localization and synthesis, reviewing widely used datasets, highlighting key challenges, and providing an organized overview of state-of-the-art techniques. Furthermore, it discusses current limitations, offers comparative analyses, and outlines promising directions for future research. We also include the project page via https://github.com/GDAOSU/Awesome-Cross-View-Methods.

Shuang Song, Zhaopeng Cui, Rongjun Qin

We present a novel framework for mesh reconstruction from unstructured point clouds by taking advantage of the learned visibility of the 3D points in the virtual views and traditional graph-cut based mesh generation. Specifically, we first propose a three-step network that explicitly employs depth completion for visibility prediction. Then the visibility information of multiple views is aggregated to generate a 3D mesh model by solving an optimization problem considering visibility in which a novel adaptive visibility weighting in surface determination is also introduced to suppress line of sight with a large incident angle. Compared to other learning-based approaches, our pipeline only exercises the learning on a 2D binary classification task, \ie, points visible or not in a view, which is much more generalizable and practically more efficient and capable to deal with a large number of points. Experiments demonstrate that our method with favorable transferability and robustness, and achieve competing performances \wrt state-of-the-art learning-based approaches on small complex objects and outperforms on large indoor and outdoor scenes. Code is available at https://github.com/GDAOSU/vis2mesh.

Shuang Song, Debao Huang, Deyan Deng et al.

Intrinsic image decomposition (IID) of outdoor scenes is crucial for relighting, editing, and understanding large-scale environments, but progress has been limited by the lack of real-world datasets with reliable albedo and shading supervision. We introduce Olbedo, a large-scale aerial dataset for outdoor albedo--shading decomposition in the wild. Olbedo contains 5,664 UAV images captured across four landscape types, multiple years, and diverse illumination conditions. Each view is accompanied by multi-view consistent albedo and shading maps, metric depth, surface normals, sun and sky shading components, camera poses, and, for recent flights, measured HDR sky domes. These annotations are derived from an inverse-rendering refinement pipeline over multi-view stereo reconstructions and calibrated sky illumination, together with per-pixel confidence masks. We demonstrate that Olbedo enables state-of-the-art diffusion-based IID models, originally trained on synthetic indoor data, to generalize to real outdoor imagery: fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark. We further illustrate applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins. We release the dataset, baseline models, and an evaluation protocol to support future research in outdoor intrinsic decomposition and illumination-aware aerial vision.

Zhuoxiao Li, Shanliang Yao, Taoyu Wu et al.

While Gaussian Splatting (GS) demonstrates efficient and high-quality scene rendering and small area surface extraction ability, it falls short in handling large-scale aerial image surface extraction tasks. To overcome this, we present ULSR-GS, a framework dedicated to high-fidelity surface extraction in ultra-large-scale scenes, addressing the limitations of existing GS-based mesh extraction methods. Specifically, we propose a point-to-photo partitioning approach combined with a multi-view optimal view matching principle to select the best training images for each sub-region. Additionally, during training, ULSR-GS employs a densification strategy based on multi-view geometric consistency to enhance surface extraction details. Experimental results demonstrate that ULSR-GS outperforms other state-of-the-art GS-based works on large-scale aerial photogrammetry benchmark datasets, significantly improving surface extraction accuracy in complex urban environments. Project page: https://ulsrgs.github.io.

Ningli Xu, Rongjun Qin

Generating consistent ground-view images from satellite imagery is challenging, primarily due to the large discrepancies in viewing angles and resolution between satellite and ground-level domains. Previous efforts mainly concentrated on single-view generation, often resulting in inconsistencies across neighboring ground views. In this work, we propose a novel cross-view synthesis approach designed to overcome these challenges by ensuring consistency across ground-view images generated from satellite views. Our method, based on a fixed latent diffusion model, introduces two conditioning modules: satellite-guided denoising, which extracts high-level scene layout to guide the denoising process, and satellite-temporal denoising, which captures camera motion to maintain consistency across multiple generated views. We further contribute a large-scale satellite-ground dataset containing over 100,000 perspective pairs to facilitate extensive ground scene or video generation. Experimental results demonstrate that our approach outperforms existing methods on perceptual and temporal metrics, achieving high photorealism and consistency in multi-view outputs.

Steven Landgraf, Rongjun Qin, Markus Ulrich

While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting absolute distances, poses particular challenges, as even the most advanced foundation models remain prone to critical errors. Since quantifying the uncertainty has emerged as a promising endeavor to address these limitations and enable trustworthy deployment, we fuse five different uncertainty quantification methods with the current state-of-the-art DepthAnythingV2 foundation model. To cover a wide range of metric depth domains, we evaluate their performance on four diverse datasets. Our findings identify fine-tuning with the Gaussian Negative Log-Likelihood Loss (GNLL) as a particularly promising approach, offering reliable uncertainty estimates while maintaining predictive performance and computational efficiency on par with the baseline, encompassing both training and inference time. By fusing uncertainty quantification and foundation models within the context of monocular depth estimation, this paper lays a critical foundation for future research aimed at improving not only model performance but also its explainability. Extending this critical synthesis of uncertainty quantification and foundation models into other crucial tasks, such as semantic segmentation and pose estimation, presents exciting opportunities for safer and more reliable machine vision systems.

Shuang Song, Yang Tang, Rongjun Qin

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and locations. However, the amount of time-consuming annotated data for capturing worldwide diversity may never catch up with the demands of increasingly data-hungry models. Thus, we propose a novel approach: re-training models at test time using synthetic data tailored to the target region's city layout. This method generates geo-typical synthetic data that closely replicates the urban structure of a target area by leveraging geospatial data such as street network from OpenStreetMap. Using procedural modeling and physics-based rendering, very high-resolution synthetic images are created, incorporating domain randomization in building shapes, materials, and environmental illumination. This enables the generation of virtually unlimited training samples that maintain the essential characteristics of the target environment. To overcome synthetic-to-real domain gaps, our approach integrates geo-typical data into an adversarial domain adaptation framework for building segmentation. Experiments demonstrate significant performance enhancements, with median improvements of up to 12%, depending on the domain gap. This scalable and cost-effective method blends partial geographic knowledge with synthetic imagery, providing a promising solution to the "model collapse" issue in purely synthetic datasets. It offers a practical pathway to improving generalization in remote sensing building segmentation without extensive real-world annotations.

Zhenxin Zhang, Zhihua Xu, Yuwei Cao et al.

Point cloud processing as a fundamental task in the field of geomatics and computer vision, has been supporting tasks and applications at different scales from air to ground, including mapping, environmental monitoring, urban/tree structure modeling, automated driving, robotics, disaster responses etc. Due to the rapid development of deep learning, point cloud processing algorithms have nowadays been almost explicitly dominated by learning-based approaches, most of which are yet transitioned into real-world practices. Existing surveys primarily focus on the ever-updating network architecture to accommodate unordered point clouds, largely ignoring their practical values in typical point cloud processing applications, in which extra-large volume of data, diverse scene contents, varying point density, data modality need to be considered. In this paper, we provide a meta review on deep learning approaches and datasets that cover a selection of critical tasks of point cloud processing in use such as scene completion, registration, semantic segmentation, and modeling. By reviewing a broad range of urban and environmental applications these tasks can support, we identify gaps to be closed as these methods transformed into applications and draw concluding remarks in both the algorithmic and practical aspects of the surveyed methods.

Xinyi Wu, Steven Landgraf, Markus Ulrich et al.

State-of-the-art 3D computer vision algorithms continue to advance in handling sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R), Matching and Stereo 3D Reconstruction (MASt3R), and Visual Geometry Grounded Transformer (VGGT), have attracted attention due to their ability to handle very sparse image overlaps. Evaluating DUSt3R/MASt3R/VGGT on typical aerial images matters, as these models may handle extremely low image overlaps, stereo occlusions, and textureless regions. For redundant collections, they can accelerate 3D reconstruction by using extremely sparsified image sets. Despite tests on various computer vision benchmarks, their potential on photogrammetric aerial blocks remains unexplored. This paper conducts a comprehensive evaluation of the pre-trained DUSt3R/MASt3R/VGGT models on the aerial blocks of the UseGeo dataset for pose estimation and dense 3D reconstruction. Results show these methods can accurately reconstruct dense point clouds from very sparse image sets (fewer than 10 images, up to 518 pixels resolution), with completeness gains up to +50% over COLMAP. VGGT also demonstrates higher computational efficiency, scalability, and more reliable camera pose estimation. However, all exhibit limitations with high-resolution images and large sets, as pose reliability declines with more images and geometric complexity. These findings suggest transformer-based methods cannot fully replace traditional SfM and MVS, but offer promise as complementary approaches, especially in challenging, low-resolution, and sparse scenarios.

Debao Huang, Rongjun Qin

Uncertainty quantification of the photogrammetry process is essential for providing per-point accuracy credentials of the point clouds. Unlike airborne LiDAR, which typically delivers consistent accuracy across various scenes, the accuracy of photogrammetric point clouds is highly scene-dependent, since it relies on algorithm-generated measurements (i.e., stereo or multi-view stereo). Generally, errors of the photogrammetric point clouds propagate through a two-step process: Structure-from-Motion (SfM) with Bundle adjustment (BA), followed by Multi-view Stereo (MVS). While uncertainty estimation in the SfM stage has been well studied using the first-order statistics of the reprojection error function, that in the MVS stage remains largely unsolved and non-standardized, primarily due to its non-differentiable and multi-modal nature (i.e., from pixel values to geometry). In this paper, we present an uncertainty quantification framework closing this gap by associating an error covariance matrix per point accounting for this two-step photogrammetry process. Specifically, to estimate the uncertainty in the MVS stage, we propose a novel, self-calibrating method by taking reliable n-view points (n>=6) per-view to regress the disparity uncertainty using highly relevant cues (such as matching cost values) from the MVS stage. Compared to existing approaches, our method uses self-contained, reliable 3D points extracted directly from the MVS process, with the benefit of being self-supervised and naturally adhering to error propagation path of the photogrammetry process, thereby providing a robust and certifiable uncertainty quantification across diverse scenes. We evaluate the framework using a variety of publicly available airborne and UAV imagery datasets. Results demonstrate that our method outperforms existing approaches by achieving high bounding rates without overestimating uncertainty.

Pengfei Zhang, Chang Li, Yongjun Zhang et al.

Remotely sensed imagery interpretation (RSII) faces the three major problems: (1) objective representation of spatial distribution patterns; (2) edge uncertainty problem caused by downsampling encoder and intrinsic edge noises (e.g., mixed pixel and edge occlusion etc.); and (3) false detection problem caused by geometric registration error in change detection. To solve the aforementioned problems, uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed, whose superiorities are as follows: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially frequency-wise stationary and non-stationary features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP proposes high-frequency-wise stream to replace high-resolution-wise stream in HRFormer through the whole encoder-decoder process with parallel frequency-wise high-to-low streams, so it improves the edge extraction accuracy by continuously remaining high-frequency information; (2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM), which is a self-supervised learning strategy, is proposed to improve the edge accuracy of extraction and change detection by gradually removing the simulated spectrum noises based on geo-knowledge and the generated diffused spectrum noises; (3) a frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection. Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error.

Hessah Albanwan, Rongjun Qin, Yang Tang

Image fusion in Remote Sensing (RS) has been a consistent demand due to its ability to turn raw images of different resolutions, sources, and modalities into accurate, complete, and spatio-temporally coherent images. It greatly facilitates downstream applications such as pan-sharpening, change detection, land-cover classification, etc. Yet, image fusion solutions are highly disparate to various remote sensing problems and thus are often narrowly defined in existing reviews as topical applications, such as pan-sharpening, and spatial-temporal image fusion. Considering that image fusion can be theoretically applied to any gridded data through pixel-level operations, in this paper, we expanded its scope by comprehensively surveying relevant works with a simple taxonomy: 1) many-to-one image fusion; 2) many-to-many image fusion. This simple taxonomy defines image fusion as a mapping problem that turns either a single or a set of images into another single or set of images, depending on the desired coherence, e.g., spectral, spatial/resolution coherence, etc. We show that this simple taxonomy, despite the significant modality difference it covers, can be presented by a conceptually easy framework. In addition, we provide a meta-analysis to review the major papers studying the various types of image fusion and their applications over the years (from the 1980s to date), covering 5,926 peer-reviewed papers. Finally, we discuss the main benefits and emerging challenges to provide open research directions and potential future works.

Xiao ling, Rongjun Qin

Texture mapping as a fundamental task in 3D modeling has been well established for well-acquired aerial assets under consistent illumination, yet it remains a challenge when it is scaled to large datasets with images under varying views and illuminations. A well-performed texture mapping algorithm must be able to efficiently select views, fuse and map textures from these views to mesh models, at the same time, achieve consistent radiometry over the entire model. Existing approaches achieve efficiency either by limiting the number of images to one view per face, or simplifying global inferences to only achieve local color consistency. In this paper, we break this tie by proposing a novel and efficient texture mapping framework that allows the use of multiple views of texture per face, at the same time to achieve global color consistency. The proposed method leverages a loopy belief propagation algorithm to perform an efficient and global-level probabilistic inferences to rank candidate views per face, which enables face-level multi-view texture fusion and blending. The texture fusion algorithm, being non-parametric, brings another advantage over typical parametric post color correction methods, due to its improved robustness to non-linear illumination differences. The experiments on three different types of datasets (i.e. satellite dataset, unmanned-aerial vehicle dataset and close-range dataset) show that the proposed method has produced visually pleasant and texturally consistent results in all scenarios, with an added advantage of consuming less running time as compared to the state of the art methods, especially for large-scale dataset such as satellite-derived models.

Xiao Ling, Rongjun Qin

In this paper, based on the assumption that the object boundaries (e.g., buildings) from the over-view data should coincide with footprints of façade 3D points generated from street-view photogrammetric images, we aim to address this problem by proposing a fully automated geo-registration method for cross-view data, which utilizes semantically segmented object boundaries as view-invariant features under a global optimization framework through graph-matching: taking the over-view point clouds generated from stereo/multi-stereo satellite images and the street-view point clouds generated from monocular video images as the inputs, the proposed method models segments of buildings as nodes of graphs, both detected from the satellite-based and street-view based point clouds, thus to form the registration as a graph-matching problem to allow non-rigid matches; to enable a robust solution and fully utilize the topological relations between these segments, we propose to address the graph-matching problem on its conjugate graph solved through a belief-propagation algorithm. The matched nodes will be subject to a further optimization to allow precise-registration, followed by a constrained bundle adjustment on the street-view image to keep 2D29 3D consistencies, which yields well-registered street-view images and point clouds to the satellite point clouds.

Rongjun Qin, Tao Liu

As an important application in remote sensing, landcover classification remains one of the most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly increasing number of Deep Learning (DL) based landcover methods and training strategies are claimed to be the state-of-the-art, the already fragmented technical landscape of landcover mapping methods has been further complicated. Although there exists a plethora of literature review work attempting to guide researchers in making an informed choice of landcover mapping methods, the articles either focus on the review of applications in a specific area or revolve around general deep learning models, which lack a systematic view of the ever advancing landcover mapping methods. In addition, issues related to training samples and model transferability have become more critical than ever in an era dominated by data-driven approaches, but these issues were addressed to a lesser extent in previous review articles regarding remote sensing classification. Therefore, in this paper, we present a systematic overview of existing methods by starting from learning methods and varying basic analysis units for landcover mapping tasks, to challenges and solutions on three aspects of scalability and transferability with a remote sensing classification focus including (1) sparsity and imbalance of data; (2) domain gaps across different geographical regions; and (3) multi-source and multi-view fusion. We discuss in detail each of these categorical methods and draw concluding remarks in these developments and recommend potential directions for the continued endeavor.

Shengxi Gui, Rongjun Qin

In this paper, we propose a model-driven method that reconstructs LoD-2 building models following a "decomposition-optimization-fitting" paradigm. The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a "three-step" polygon extraction method, followed by a novel grid-based decomposition method that decomposes the complex and irregularly shaped building polygons to tightly combined elementary building rectangles ready to fit elementary building models. We have optionally introduced OpenStreetMap (OSM) and Graph-Cut (GC) labeling to further refine the orientation of 2D building rectangle. The 3D modeling step takes building-specific parameters such as hip lines, as well as non-rigid and regularized transformations to optimize the flexibility for using a minimal set of elementary models. Finally, roof type of building models s refined and adjacent building models in one building segment are merged into the complex polygonal model. Our proposed method has addressed a few technical caveats over existing methods, resulting in practically high-quality results, based on our evaluation and comparative study on a diverse set of experimental datasets of cities with different urban patterns.

Rongjun Qin, Armin Gruen, Cive Fraser

Recently developed automatic dense image matching algorithms are now being implemented for DSM/DTM production, with their pixel-level surface generation capability offering the prospect of partially alleviating the need for manual and semi-automatic stereoscopic measurements. In this paper, five commercial/public software packages for 3D surface generation are evaluated, using 5cm GSD imagery recorded from a UAV. Generated surface models are assessed against point clouds generated from mobile LiDAR and manual stereoscopic measurements. The software packages considered are APS, MICMAC, SURE, Pix4UAV and an SGM implementation from DLR.

Ningli Xu, Debao Huang, Shuang Song et al.

In this paper, we present a case study that performs an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event. Multi-temporal oblique photogrammetry images are collected with 3D point clouds generated at different stages of the demolition. The geometric accuracy of the generated point clouds has been evaluated against both airborne and terrestrial LiDAR point clouds, achieving an average distance of 12 cm and 16 cm for roof and facade respectively. We propose a hierarchical volumetric change detection framework that unifies multi-temporal UAV images for pose estimation (free of ground control points), reconstruction, and a coarse-to-fine 3D density change analysis. This work has provided a solution capable of addressing change detection on full 3D time-series datasets where dramatic scene content changes are presented progressively. Our change detection results on the building demolition event have been evaluated against the manually marked ground-truth changes and have achieved an F-1 score varying from 0.78 to 0.92, with consistently high precision (0.92 - 0.99). Volumetric changes through the demolition progress are derived from change detection and have shown to favorably reflect the qualitative and quantitative building demolition progression.

Hessah Albanwan, Rongjun Qin

Remote sensing images and techniques are powerful tools to investigate earth surface. Data quality is the key to enhance remote sensing applications and obtaining a clear and noise-free set of data is very difficult in most situations due to the varying acquisition (e.g., atmosphere and season), sensor, and platform (e.g., satellite angles and sensor characteristics) conditions. With the increasing development of satellites, nowadays Terabytes of remote sensing images can be acquired every day. Therefore, information and data fusion can be particularly important in the remote sensing community. The fusion integrates data from various sources acquired asynchronously for information extraction, analysis, and quality improvement. In this chapter, we aim to discuss the theory of spatiotemporal fusion by investigating previous works, in addition to describing the basic concepts and some of its applications by summarizing our prior and ongoing works.

Xiao Ling, Xu Huang, Rongjun Qin

Bundle adjustment (BA) is a technique for refining sensor orientations of satellite images, while adjustment accuracy is correlated with feature matching results. Feature match-ing often contains high uncertainties in weak/repeat textures, while BA results are helpful in reducing these uncertainties. To compute more accurate orientations, this article incorpo-rates BA and feature matching in a unified framework and formulates the union as the optimization of a global energy function so that the solutions of the BA and feature matching are constrained with each other. To avoid a degeneracy in the optimization, we propose a comprised solution by breaking the optimization of the global energy function into two-step suboptimizations and compute the local minimums of each suboptimization in an incremental manner. Experiments on multi-view high-resolution satellite images show that our proposed method outperforms state-of-the-art orientation techniques with or without accurate least-squares matching.

Changlin Xiao, Rongjun Qin, Xiao Xie et al.

Individual tree detection and crown delineation (ITDD) are critical in forest inventory management and remote sensing based forest surveys are largely carried out through satellite images. However, most of these surveys only use 2D spectral information which normally has not enough clues for ITDD. To fully explore the satellite images, we propose a ITDD method using the orthophoto and digital surface model (DSM) derived from the multi-view satellite data. Our algorithm utilizes the top-hat morphological operation to efficiently extract the local maxima from DSM as treetops, and then feed them to a modi-fied superpixel segmentation that combines both 2D and 3D information for tree crown delineation. In subsequent steps, our method incorporates the biological characteristics of the crowns through plant allometric equation to falsify potential outliers. Experiments against manually marked tree plots on three representative regions have demonstrated promising results - the best overall detection accuracy can be 89%.

Hessah Albanwan, Rongjun Qin, Xiaohu Lu et al.

The current practice in land cover/land use change analysis relies heavily on the individually classified maps of the multitemporal data set. Due to varying acquisition conditions (e.g., illumination, sensors, seasonal differences), the classification maps yielded are often inconsistent through time for robust statistical analysis. 3D geometric features have been shown to be stable for assessing differences across the temporal data set. Therefore, in this article we investigate he use of a multitemporal orthophoto and digital surface model derived from satellite data for spatiotemporal classification. Our approach consists of two major steps: generating per-class probability distribution maps using the random-forest classifier with limited training samples, and making spatiotemporal inferences using an iterative 3D spatiotemporal filter operating on per-class probability maps. Our experimental results demonstrate that the proposed methods can consistently improve the individual classification results by 2%-6% and thus can be an important postclassification refinement approach.

Rongjun Qin

The geodatabase (vectorized data) nowadays becomes a rather standard digital city infrastructure; however, updating geodatabase efficiently and economically remains a fundamental and practical issue in the geospatial industry. The cost of building a geodatabase is extremely high and labor intensive, and very often the maps we use have several months and even years of latency. One solution is to develop more automated methods for (vectorized) geospatial data generation, which has been proven a difficult task in the past decades. An alternative solution is to first detect the differences between the new data and the existing geospatial data, and then only update the area identified as changes. The second approach is becoming more favored due to its high practicality and flexibility. A highly relevant technique is change detection. This article aims to provide an overview the state-of-the-art change detection methods in the field of Remote Sensing and Geomatics to support the task of updating geodatabases. Data used for change detection are highly disparate, we therefore structure our review intuitively based on the dimension of the data, being 1) change detection with 2D data; 2) change detection with 3D data. Conclusions will be drawn based on the reviewed efforts in the field, and we will share our outlooks of the topic of updating geodatabases.

Rongjun Qin, Xu Huang

Image-based 3D object modeling refers to the process of converting raw optical images to 3D digital representations of the objects. Very often, such models are desired to be dimensionally true, semantically labeled with photorealistic appearance (reality-based modeling). Laser scanning was deemed as the standard (and direct) way to obtaining highly accurate 3D measurements of objects, while one would have to abide the high acquisition cost and its unavailability on some of the platforms. Nowadays the image-based methods backboned by the recently developed advanced dense image matching algorithms and geo-referencing paradigms, are becoming the dominant approaches, due to its high flexibility, availability and low cost. The largely automated geometric processing of images in a 3D object reconstruction workflow, from ordered/unordered raw imagery to textured meshes, is becoming a critical part of the reality-based 3D modeling. This article summarizes the overall geometric processing workflow, with focuses on introducing the state-of-the-art methods of three major components of geometric processing: 1) geo-referencing; 2) Image dense matching 3) texture mapping. Finally, we will draw conclusions and share our outlooks of the topics discussed in this article.

Rongjun Qin, Shuang Song, Xiao Ling et al.

3D recovery from multi-stereo and stereo images, as an important application of the image-based perspective geometry, serves many applications in computer vision, remote sensing and Geomatics. In this chapter, the authors utilize the imaging geometry and present approaches that perform 3D reconstruction from cross-view images that are drastically different in their viewpoints. We introduce our framework that takes ground-view images and satellite images for full 3D recovery, which includes necessary methods in satellite and ground-based point cloud generation from images, 3D data co-registration, fusion and mesh generation. We demonstrate our proposed framework on a dataset consisting of twelve satellite images and 150k video frames acquired through a vehicle-mounted Go-pro camera and demonstrate the reconstruction results. We have also compared our results with results generated from an intuitive processing pipeline that involves typical geo-registration and meshing methods.

Rongjun Qin, Songyi Gao, Xingyuan Zhang et al.

Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they involve large datasets collected by highly exploratory policies, and the trained policy is directly evaluated in the environment. In real-world situations, running a highly exploratory policy is prohibited to ensure system safety, the data is commonly very limited, and a trained policy should be well validated before deployment. In this paper, we present a near real-world offline RL benchmark, named NeoRL, which contains datasets from various domains with controlled sizes, and extra test datasets for policy validation. We evaluate existing offline RL algorithms on NeoRL and argue that the performance of a policy should also be compared with the deterministic version of the behavior policy, instead of the dataset reward. The empirical results demonstrate that the tested offline RL algorithms become less competitive to the deterministic policy on many datasets, and the offline policy evaluation hardly helps. The NeoRL suit can be found at http://polixir.ai/research/neorl. We hope this work will shed some light on future research and draw more attention when deploying RL in real-world systems.

Zuoyue Li, Zhenqiang Li, Zhaopeng Cui et al.

We present a novel method for synthesizing both temporally and geometrically consistent street-view panoramic video from a single satellite image and camera trajectory. Existing cross-view synthesis approaches focus on images, while video synthesis in such a case has not yet received enough attention. For geometrical and temporal consistency, our approach explicitly creates a 3D point cloud representation of the scene and maintains dense 3D-2D correspondences across frames that reflect the geometric scene configuration inferred from the satellite view. As for synthesis in the 3D space, we implement a cascaded network architecture with two hourglass modules to generate point-wise coarse and fine features from semantics and per-class latent vectors, followed by projection to frames and an upsampling module to obtain the final realistic video. By leveraging computed correspondences, the produced street-view video frames adhere to the 3D geometric scene structure and maintain temporal consistency. Qualitative and quantitative experiments demonstrate superior results compared to other state-of-the-art synthesis approaches that either lack temporal consistency or realistic appearance. To the best of our knowledge, our work is the first one to synthesize cross-view images to video.