ZeD-MAP: Bundle Adjustment Guided Zero-Shot Depth Maps for Real-Time Aerial Imaging

• URL: http://arxiv.org/abs/2604.04667v1
• Date: Mon, 06 Apr 2026 13:21:17 GMT
• Title: ZeD-MAP: Bundle Adjustment Guided Zero-Shot Depth Maps for Real-Time Aerial Imaging
• Abstract summary: ZeD-MAP is a cluster-level framework that converts a test-time diffusion depth model into a metrically consistent, SLAM-like mapping pipeline.<n>We show that our method achieves sub-meter accuracy, with approximately 0.87 m error in the horizontal (XY) plane and 0.12 m in the vertical (Z) direction.<n>Results are subject to minor noise from manual point-cloud annotation.
• Score: 1.9247157750972368
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time depth reconstruction from ultra-high-resolution UAV imagery is essential for time-critical geospatial tasks such as disaster response, yet remains challenging due to wide-baseline parallax, large image sizes, low-texture or specular surfaces, occlusions, and strict computational constraints. Recent zero-shot diffusion models offer fast per-image dense predictions without task-specific retraining, and require fewer labelled datasets than transformer-based predictors while avoiding the rigid capture geometry requirement of classical multi-view stereo. However, their probabilistic inference prevents reliable metric accuracy and temporal consistency across sequential frames and overlapping tiles. We present ZeD-MAP, a cluster-level framework that converts a test-time diffusion depth model into a metrically consistent, SLAM-like mapping pipeline by integrating incremental cluster-based bundle adjustment (BA). Streamed UAV frames are grouped into overlapping clusters; periodic BA produces metrically consistent poses and sparse 3D tie-points, which are reprojected into selected frames and used as metric guidance for diffusion-based depth estimation. Validation on ground-marker flights captured at approximately 50 m altitude (GSD is approximately 0.85 cm/px, corresponding to 2,650 square meters ground coverage per frame) with the DLR Modular Aerial Camera System (MACS) shows that our method achieves sub-meter accuracy, with approximately 0.87 m error in the horizontal (XY) plane and 0.12 m in the vertical (Z) direction, while maintaining per-image runtimes between 1.47 and 4.91 seconds. Results are subject to minor noise from manual point-cloud annotation. These findings show that BA-based metric guidance provides consistency comparable to classical photogrammetric methods while significantly accelerating processing, enabling real-time 3D map generation.

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos [76.81099730054356]
  We present OrthoTrack, a training-free system that estimates continuous 6-DoF trajectories using only publicly available orthophotos and surface models as a map prior.<n>On MovingDrone and real-world benchmarks, OrthoTrack runs in real time on a single GPU. It outperforms all baselines by a large margin, even those receiving oracle scale and alignment.
  arXiv  Detail & Related papers  (2026-06-24T00:05:01Z)
• Interp3R: Continuous-time 3D Geometry Estimation with Frames and Events [19.851795807287633]
  We introduce Interp3R, which enhances pointmap-based models to estimate depth and camera poses at arbitrary time instants.<n>We train Interp3R exclusively on a synthetic dataset, yet demonstrate strong generalization across a wide range of synthetic and real-world benchmarks.
  arXiv  Detail & Related papers  (2026-03-15T18:10:05Z)
• Super4DR: 4D Radar-centric Self-supervised Odometry and Gaussian-based Map Optimization [13.79944715452315]
  We propose Super4DR, a 4D radar-centric framework for learning-based odometry estimation and map optimization.<n>Super4DR achieves a 67% performance gain over prior self-supervised methods, nearly matches supervised odometry, and narrows the map quality disparity with LiDAR.<n> Experiments show that Super4DR achieves a 67% performance gain over prior self-supervised methods, nearly matches supervised odometry, and narrows the map quality disparity with LiDAR.
  arXiv  Detail & Related papers  (2025-12-10T12:55:05Z)
• Real-Time Bundle Adjustment for Ultra-High-Resolution UAV Imagery Using Adaptive Patch-Based Feature Tracking [1.9247157750972368]
  We propose a novel real-time BA framework that operates directly on fullresolution UAV imagery without downsampling.<n>Our lightweight, onboard-compatible approach divides each image into user-defined patches and tracks them across frames.<n>Overlapping relationships between images are determined in real time using UAV navigation system.<n>The proposed algorithm is designed for seamless integration into the DLR Modular Aerial Camera System.
  arXiv  Detail & Related papers  (2025-11-08T22:09:32Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification [0.6445605125467574]
  We present a neural radiance field (NeRF) based large-scale reconstruction system that fuses lidar and vision data.<n>Our system adopts the state-of-the-art NeRF representation to incorporate lidar.<n>Adding lidar data adds strong geometric constraints on the depth and surface normals.
  arXiv  Detail & Related papers  (2025-02-04T19:00:49Z)
• ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras [41.992980062962495]
  Event-based visual odometry aims at solving tracking and mapping subproblems (typically in parallel)<n>We build an event-based stereo visual-inertial odometry system on top of a direct pipeline.<n>The resulting system scales well with modern high-resolution event cameras.
  arXiv  Detail & Related papers  (2024-10-12T05:35:27Z)
• A Large Scale Homography Benchmark [52.55694707744518]
  We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset. We also present HEB, a large-scale homography estimation benchmark leveraging Pi3D.
  arXiv  Detail & Related papers  (2023-02-20T14:18:09Z)
• Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography [54.36608424943729]
  We show that in a ''long-burst'', forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. We devise a test-time optimization approach that fits a neural RGB-D representation to long-burst data and simultaneously estimates scene depth and camera motion.
  arXiv  Detail & Related papers  (2022-12-22T18:54:34Z)
• Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization [18.466941045530408]
  Non-line-of-sight imaging technique aims to reconstruct targets from multiply reflected light. We propose a signal-surface collaborative regularization framework that provides noise-robust reconstructions with a minimal number of measurements. Our approach has great potential in real-time non-line-of-sight imaging applications such as rescue operations and autonomous driving.
  arXiv  Detail & Related papers  (2022-11-21T11:19:20Z)

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.