🛰️ Remote Sensing

🎞️ ECCV2026 · 39 paper notes

📌 Same area in other venues: 📷 CVPR2026 (63) · 🔬 ICLR2026 (11) · 🧪 ICML2026 (3) · 🤖 AAAI2026 (7) · 🧠 NeurIPS2025 (12) · 📹 ICCV2025 (11)

🔥 Top topics: Remote Sensing ×14 · Re-Identification ×4 · Segmentation ×3 · Multimodal/VLM ×2 · Alignment/RLHF ×2

OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents

OpenEarthAgent connects visual perception, GIS, spectral indices, and georeferenced raster operations to a unified executor, then fine-tunes Qwen3-4B on replay-validated trajectories, improving strict tool-order matching from 14.71% to 67.24% on its test set while non-generation answer accuracy remains only 45.26%.

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training

MMEarth-Bench evaluates geographic generalization with five global environmental tasks and twelve aligned modalities, then adapts encoders by reconstructing these modalities at test time; relative to joint training, TTT-MMR improves aggregate results across tasks and both test splits, with geographic batching particularly helpful for long-tail samples.

Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing

Moonstone aligns 28 channels from seven instrument families aboard five lunar orbiters into a single global map at 128 pixels per degree (~237 m/pixel), pretrains the self-supervised masked autoencoder MG-MAE with modality-grouped tokenizers, a shared ViT, coverage-adaptive masking and missing-modality attention masking, and reports the first multimodal lunar downstream benchmark (six classification/regression/segmentation tasks), beating scratch, ImageNet, Earth-observation foundation models and vanilla MAE by large margins — +16.2% geology accuracy and +14.7 mIoU crater segmentation.

TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

TerraDiT-Ω lets a diffusion transformer consume native geospatial primitives (polygons, polylines, bounding boxes, points) directly as spatial control: a Unified Primitive Encoder maps all four formats into one shared instance token, and Geometry-Aware Local Attention multiplies explicit geometric priors — a rotated anisotropic Gaussian plus a dense spatial geometry field — into the attention logits, beating both dense-raster and sparse-prompt baselines across all conditioning formats and serving as a single model for synthetic data augmentation on four remote sensing tasks.

Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization

GAGeo adapts the 3D foundation model π3 using CMA-Loc building correspondences and camera annotations, jointly decodes prompted objects and cameras in one forward pass, and uses satellite-anchored contrastive learning to reach 43.86 mAcc and 57.88 mIoU on the untrained ground-to-drone configuration.

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

CROSS distills text-filtered patch-to-patch geometric affinities from the SAM 2 encoder into the shallow, deep, and final layers of SigLIP 2 as a soft structural regularizer, then adds dual-constrained contrastive learning (perceptive hard negatives plus spatial counterfactual texts) to break the object-centric shortcut, reaching 83.25 cIoU and 41.32 [email protected] on RefSegRS.

G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening

G-ZAP uses a scale-conditioned implicit neural representation (INR) as its pansharpening fusion backbone, trained by a three-level collaborative scheme — an unsupervised spectral consistency loss at full resolution plus two levels of constructed supervision at reduced resolutions — so that a model trained on nothing but the test image pair itself produces HRMS output at any magnification, and the learned weights transfer directly to unseen image pairs, scenes, and sensors.

GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision

GeoSolver trains the token-level GeoPRM through entropy-guided tree search and visual hallucination injection, then integrates it into Process-Aware Tree-GRPO and test-time search to constrain intermediate visual evidence as well as final answers; in the paper's Table 3, visual grounding improves from 58.19 to 68.04 with a generation budget of 32.

PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection

PKINet-v2 combines heterogeneous kernels to address object geometry and scale in remote sensing, then equivalently merges its training-time aggregation branches for deployment, achieving 80.46% mAP and 54.60 FPS on single-scale DOTA-v1.0 versus 78.39% and 14.05 FPS for PKINet-v1-S.

Recurrent Cross-View Object Geo-Localization

ReCOT repeatedly reads satellite features with learnable tokens carrying the queried object's semantics, supported by SAM distillation and reference feature enhancement, achieving 48.10% Ground-to-Satellite and 72.05% Drone-to-Satellite [email protected] on the CVOGL test set with 29.9M parameters.

Warp-free Cross-view Geo-localization via Feature-space Consensus Mining

The paper proposes a joint-view consensus-guided learning framework for cross-view geo-localization: during training an auxiliary joint-view pathway serves as a semantic anchor, a globally shared set of pattern probes projects the street, satellite, and joint streams into one strictly aligned metric space, and a consensus-mediated contrastive objective pulls the single-view embeddings toward that anchor — yielding state-of-the-art results on CVUSA, CVACT, VIGOR, and University-1652 with no geometric warping at all, and zero extra cost at inference because the joint branch is discarded.

Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels

Align and Segment (AnS) jointly learns building segmentation and geometric label correction, using self-supervised consistency and paired geometric augmentation to prevent memorized offsets, raising segmentation IoU from 0.39 for naive joint training to 0.78 on systematically misaligned Las Vegas data without clean aligned training labels.

EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

EoS-FM introduces an Ensemble-of-Specialists framework for remote sensing that combines 22 lightweight, frozen ConvNeXtV2-Atto specialist encoders via physics-aware band adaptation, feature batch normalization, and a differentiable top-k tail-\(\ell_1\) selection layer, achieving the best average Distance-To-Best (4.58 Avg. DTB) across 11 Pangaea benchmark tasks with only 76M parameters (22M in EoS-FM Small).

Estimating Individual Tree Height and Species from UAV Imagery

This paper introduces BIRCH-Trees, the first benchmark for simultaneous tree height regression and fine-grained species classification from tree-centered monocular RGB UAV imagery, and proposes DINOvTree, an efficient multi-task framework with a shared foundation model backbone that outperforms separate task-specific models using nearly half the parameters.

GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data

GroundSet introduces a large-scale Earth Observation spatial grounding benchmark grounded in legally verified 20cm aerial orthophotos and cadastral vector data from the French National Mapping Agency (IGN), containing 510k images, 3.8M objects across 135 granular classes, and demonstrates that a vanilla LLaVA-1.6 architecture fine-tuned on this data significantly outperforms existing RS specialists and commercial models like Gemini-2.5 on complex grounding tasks.

On-Orbit Real-Time Wildfire Detection Under On-Board Constraints

Addressing the extreme computational bottlenecks of LEO thermal microsatellites and uncalibrated single-band mid-wave infrared data, this paper introduces DenseMAE—a lightweight fully convolutional masked autoencoder paired with a high-resolution refinement head—achieving a 0.699 pixel-level full-distribution AP and 0.744 event-level Fire-F1 with a sub-megabyte footprint and 65 ms TensorRT inference.

OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization

OpenCVL introduces the first fully permissive, large-scale dataset for fine-grained cross-view localization containing over 617,000 ground-aerial image pairs across 41 cities in 4 European countries, featuring a LiDAR-guided pose correction framework for crowdsourced imagery and proving that training on diverse noisy data significantly boosts cross-view localization generalization.

Uncertainty-aware tree height change regression

The paper introduces the Canopy Height Change (CHC) benchmark dataset covering 10,598 km² at 3 m resolution with pixel-wise continuous canopy height difference and rigorous uncertainty estimates, demonstrating that uncertainty-weighted regression losses substantially improve downstream performance while foundation models still lag behind supervised baselines.

Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications

To address the lack of scalable benchmarks and representations for gated community recognition, this paper constructs GBA-GCs, a metropolitan-scale multimodal benchmark of 37,444 residential compounds in China's Greater Bay Area, and proposes the MCGC framework that fuses interior–exterior dual-stream visual contrast with modality-aware cross-attention and gating, revealing substantial enclosure-induced distortions in perceived urban greenery and pedestrian detours.

Beyond Attention: Convolutional Global Context for Remote Sensing Change Detection

ChangeGCC conditions convolution kernels on scene-level descriptors, then combines intra-frame cross-scale aggregation with symmetric cross-temporal gating to detect remote sensing changes without a global pairwise attention matrix; its Base variant achieves 85.28% IoU on LEVIR-CD with 13.60M parameters.

Capturing Spectral and Spatial Patterns for Federated Remote Sensing Segmentation

Rather than requiring every remote-sensing client to use identical class centers, FedDap applies constrained local modulation to shared prototypes using spectral and spatial cues, reporting 70.42% mIoU on the compound-shift Potsdam(IRRG) versus Vaihingen(RGB) setting, 1.60 percentage points above FedSeg.

Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion

Presents a compact, low-cost snapshot hyperspectral imaging system that converts kaleidoscope angular diversity into birefringent spectral diversity, optimizing hardware parameters via condition numbers to achieve fast, stable, and non-learning pixel-wise reconstruction across 25 spectral bands.

Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification

CAJA turns neighborhood composition and mixing around a center pixel into shared training-time context, using it to calibrate supervision and align real/pseudo-source features and predictions; without target-domain data, it raises Houston OA from FSSG's 79.98% to 85.05% without adding context-related inference steps.

CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment

CRD-Net injects frequency-separated CNN details into DINOv3, separates change-related and invariant information in bitemporal features, and uses prototype-guided hard-sample contrastive learning to recognize damage, achieving overall F1 scores of 81.26% on xBD and 81.88% on EBD without leading every subtask.

DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction

DOGE reformulates road extraction from remote sensing imagery as mask-guided curve-graph optimization: DiffAlign adjusts continuous geometry while TopoAdapt edits discrete connectivity, achieving TOPO F1 scores of 84.58 on SpaceNet and 80.59 on City-Scale without curve-level ground truth and producing more compact Bézier road networks.

Hierarchical Hyperbolic Representation Learning for Aerial-Ground Person Re-Identification

To tackle representation collapse and the suppression of view-specific details caused by forced Euclidean alignment under extreme aerial-ground viewpoint gaps, HiHR introduces Text-guided Multi-granularity Fusion (TMF) and Hierarchical Hyperbolic Learning (HHL) to preserve coarse identity separability and fine-grained view-specific cues in a Lorentz manifold, setting new state-of-the-art benchmarks on CARGO and LAGPeR.

Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments

Addressing the limitation where aerial localization benchmarks rely heavily on man-made structures and mask failure modes over natural terrain, this paper introduces Leaving the City (LTC)—a benchmark featuring 1,379 km of repeated multi-season flights, per-pixel terrain annotations, and high-precision 6-DoF ground truth—to systematically expose and quantify steep cross-domain localization degradations over unstructured landscapes.

LGD-Net: Leader-Guided Cross-Modal Dynamics for Hyperspectral and Panchromatic Image Fusion

LGD-Net proposes a hyperspectral and panchromatic fusion framework that explicitly decouples global cross-modal interaction from local multi-scale reconstruction, leveraging a continuous dynamical system on compact leader representations and discrepancy-aware graph propagation to achieve high-fidelity spectral and spatial reconstruction without increasing architectural depth.

MCVL: Multi-Space Cross-View Learning for Aerial-Ground Person Re-Identification

Addressing the severe viewpoint discrepancy and spatial-global feature gaps between UAV aerial and ground perspectives in AG-ReID, MCVL introduces an intermediate geometric projection space via Deformable Homography Transformation (DHT) combined with Cross-View Learning (CVL), alongside a memory-bank-guided View Decorrelation Contrastive Loss (VDCL) for view bias suppression, achieving state-of-the-art view-invariant and identity-discriminative representations with zero inference overhead.

MorphJEPA: Morphology-Aware Latent Prediction for Hyperspectral Images

Addressing the vulnerability of pixel reconstruction to sensor noise and the fragility of contrastive views in hyperspectral imaging, MorphJEPA introduces the first JEPA tailored to HSI by predicting embeddings of pixel-aligned morphological opening/closing targets, coupled with a disentangled cross-attention encoder and a context-anchored distribution regularizer (SIGReg), yielding substantial gains in 1/5/10-shot adaptation and cross-scene transfer.

NeSy-Route: A Neural-Symbolic Benchmark for Constrained Route Planning in Remote Sensing

NeSy-Route introduces the first large-scale neuro-symbolic benchmark for constrained route planning in remote sensing, constructing 10,821 planning instances with provably optimal trajectories via automated dual-LLM synthesis and heuristic A* search, while exposing fundamental bottlenecks of modern MLLMs in grounding symbolic constraints and formulating long-horizon spatial strategies.

OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency

Addressing device-dependent coupling in hyperspectral learning caused by band discretization discrepancy, multi-order-of-magnitude spatial resolution shifts, and severe cross-domain data imbalance, OneHSI establishes a unified, physically consistent foundation model through continuous wavelength coordinate reparameterization, scale-equivariant MoE transformation, and cross-domain adversarial representation equalization.

QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification

To tackle severe and continuous viewpoint gaps between UAVs and ground cameras, QVAM discards coarse binary view labels and rigid orthogonality constraints, distilling fine-grained viewpoint cues via learnable view queries to adaptively modulate [CLS] token representations, and incorporates dual-view momentum prototype alignment to achieve state-of-the-art cross-view matching.

Rectified Embedding Flow Learning for Aerial Multi-view Geo-localization

To tackle fine-grained cross-view distribution shifts that textual instructions fail to resolve in dense, homogeneous geographic scenes, this paper proposes Rectified Embedding Flow Learning (REFL), which formulates cross-domain alignment as a directed conditional distribution transport via continuous Ordinary Differential Equation (ODE) trajectories, achieving state-of-the-art average R@1 of 44.83% and R@10 of 65.85% on the Aerial MVGL benchmark.

SARA: Structure-Aware Riemannian-Guided Alignment for Drone Image-Text Retrieval

SARA proposes a structure-aware Riemannian-guided alignment framework for drone image-text retrieval, capturing second-order spatial topologies via symmetric positive definite (SPD) covariance descriptors on the Riemannian manifold and enforcing marginal and conditional distribution alignment in the tangent space under the Log-Euclidean metric to overcome viewpoint distortion and representation-level geometric inconsistency.

Sector-Level Cross-View Geo-Localization with Implicit Orientation via Azimuthal Scanning

Addressing the geometric mismatch and background noise between limited-FoV ground queries and omnidirectional aerial images, this paper introduces the Sector-Level Cross-View Geo-Localization (SLCVGL) task and the SectorGeo framework, which decouples aerial feature maps into overlapping azimuthal sectors to achieve fine-grained sector-level sub-region retrieval and implicit orientation estimation without continuous pose supervision.

Tessellating The Earth

TTE replaces fixed base functions (spherical harmonics/Fourier features) with learnable spherical Voronoi tessellations to encode geographic coordinates. This allows anchor stations to automatically migrate toward highly discriminative regions during training to concentrate representation capacity. Additionally, it introduces global semantic tokens as cross-regional semantic sharing channels, achieving new state-of-the-art (SOTA) performance across multiple geospatial classification and regression tasks.

Video Can Teach PAN-Sharpening: PSF-Aware Cross-Domain Supervision

ViPS introduces a cross-domain supervision framework that disentangles supervision sources into video-derived spatial supervision for high-frequency detail and misregistration recovery, and real satellite observations for spectral fidelity, bridged by sensor-specific PSF banks to achieve SOTA PAN-sharpening without real HRMS labels.

VIGA: View-Conditioned and Identity-Guided Adaptation for Aerial-Ground Person Re-Identification

Addressing extreme view geometry deformation and heavy background clutter in cross-platform aerial-ground person re-identification, VIGA suppresses background noise while preserving spatial topology via identity-guided soft masking at the feature activation level, and dynamically generates low-rank weight residual modulations for decoder feed-forward layers via a view-conditioned hypernetwork at the parameter level, achieving state-of-the-art retrieval accuracy across LAGPeR and AG-ReID.v2.