GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame

• URL: http://arxiv.org/abs/2608.29680v1
• Date: Sun, 30 Aug 2026 09:27:36 GMT
• Title: GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame
• Abstract summary: Method treats perspective-pretrained features, absolute elevation, and monocular and multi-view cues.<n> lightweight ray-consistent adapters make a frozen backbone matchable along native RPC rays.<n>bench, our absolute-frame benchmark of eighteen systems, scores absolute placement without registration or test-reference leakage.
• Score: 11.043507429399414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feed-forward 3D foundation models reconstruct perspective scenes in one pass. Satellite photogrammetry needs a different product, one that domain adaptation alone does not deliver: dense surface height in an absolute geodetic frame under non-central rational polynomial cameras (RPCs). Perspective-pretrained features are not reliably observable along RPC height rays, absolute elevation carries a low-order height--datum gauge exchangeable with sensor bias to first order, and monocular and multi-view cues fail in different regions. \method{} treats all three. Lightweight ray-consistent adapters make a frozen backbone matchable along native RPC rays. An explicit datum mechanism separates relief from absolute level and is equivariant to the vertical origin by construction, so one trained model serves zero-, one-, and sparse-control inference. Calibrated inverse-variance fusion combines the two relief streams. \bench{}, our absolute-frame benchmark of eighteen systems across in-domain, cross-dataset, and cross-city tiers, scores absolute placement without registration or test-reference leakage. On 26 held-out US3D tiles, \method{} attains $2.99$\,m absolute MAE at $91.9\%$ coverage, improves completeness-aware accuracy by $46.4$ points over the strongest compliant feed-forward baseline, remains the most accurate such system under both transfer shifts, and runs in $24$\,s model-forward time per tile. Code and models will be released at https://github.com/HIT-SIRS/GeoRay

Related papers

• A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames [8.167255229937995]
  We propose a top-down framework for metric-scale athlete localization from a single frame.<n> Boundary-Aware Adaptive Tiling mitigates boundary-splitting artifacts.<n>Second, we adapt the RTMPose-X architecture into a specialized two-keypoint estimator.<n>Third, we deterministically lift the 2D ground projections into world coordinates via camera-calibrated ray casting.
  arXiv  Detail & Related papers  (2026-09-02T15:07:24Z)
• Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real [1.7289819674602296]
  The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting.<n>We use two RGB-only routes as a controlled test of one hypothesis: that cross-view geometric consistency, not monocular depth accuracy, governs performance under Sim2Real.
  arXiv  Detail & Related papers  (2026-08-04T21:13:59Z)
• DepthART: Scaling Foundation Monocular Depth to Tiny Models [51.10174763031444]
  DepthART is a compact MDE model for on-device deployment across diverse scenes.<n>We show how DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy.<n>We also provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an GTX A6000 at $2242/4482$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.
  arXiv  Detail & Related papers  (2026-07-19T06:54:52Z)
• RayTun3R: Online Camera Adaptation in 3D Foundation Models [53.97305597591864]
  Recent 3D foundation models provide strong feed-forward depth and pose estimates on pinhole imagery, but degrade sharply under fisheye camera geometry.<n>We show that this failure is partly caused by a pinhole camera bias in the positional encodings of pretrained 3D foundation models.<n>We propose RayTun3R, a lightweight camera adaptation approach.
  arXiv  Detail & Related papers  (2026-07-02T18:55:35Z)
• SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry [69.89196162649091]
  SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry) is a novel approach for estimating 3D geometry from extended monocular video sequences.<n>Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations.
  arXiv  Detail & Related papers  (2026-06-19T10:23:25Z)
• Surflo: Consistent 3D Surface Flow Model with Global State [57.57234680235885]
  Surflo decodes oriented 3D surface points by independently transporting them from noise onto the surface via flow matching.<n>To suppress the local inconsistencies inherent to independent per-point decoding, an inference-time guidance term correlates nearby points by injecting a photometric gradient.<n>Surflo matches or surpasses feed-forward baselines on surface metrics, runs an order of magnitude faster than optimization-based methods that require hundreds of views, and is the only feed-forward approach to combine a global latent with arbitrary-resolution decoding.
  arXiv  Detail & Related papers  (2026-06-11T17:48:38Z)
• Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself [38.95274911975506]
  Free Geometry is a framework that enables feed-forward 3D reconstruction models to self-evolve at test time without any 3D ground truth.<n>Our approach consistently improves state-of-the-art foundation models, including Depth Anything 3 and VGGT, across 4 benchmark datasets.
  arXiv  Detail & Related papers  (2026-04-15T16:24:03Z)
• Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection [6.632019014616859]
  textbfCMDR-IAD is an unsupervised framework for reliable anomaly detection in 2D+3D multimodal as well as single-modality settings.<n> CMDR-IAD achieves state-of-the-art performance while operating without memory banks, reaching 97.3% image-level AUROC (I-AUROC), 99.6% pixel-level AUROC (P-AUROC), and 97.6% AUPRO.
  arXiv  Detail & Related papers  (2026-03-04T10:57:32Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images [7.144866519844918]
  Landslide monitoring is essential for understanding geohazards and mitigating associated risks.<n>Existing point cloud-based methods typically rely on either geometric or radiometric information.<n>We propose a hierarchical partition-based coarse-to-fine approach that fuses 3D point clouds and co-registered RGB images.
  arXiv  Detail & Related papers  (2025-06-19T12:28:09Z)
• LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models [36.17554088247551]
  LoRA3D is an efficient self-calibration pipeline for 3D geometric foundation models.<n>We leverage robust optimization techniques to refine multi-view predictions and align them into a global coordinate frame.<n>Our method completes the self-calibration process on a $textbfsingle standard GPU within just 5 minutes$.
  arXiv  Detail & Related papers  (2024-12-10T18:45:04Z)
• CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds [55.44204039410225]
  We present a novel two-stage fully sparse convolutional 3D object detection framework, named CAGroup3D. Our proposed method first generates some high-quality 3D proposals by leveraging the class-aware local group strategy on the object surface voxels. To recover the features of missed voxels due to incorrect voxel-wise segmentation, we build a fully sparse convolutional RoI pooling module.
  arXiv  Detail & Related papers  (2022-10-09T13:38:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.