UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction

• URL: http://arxiv.org/abs/2605.17942v2
• Date: Tue, 19 May 2026 05:33:45 GMT
• Title: UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
• Abstract summary: We introduce UAVFF3D, a geometry-aware benchmark for feed-forward UAV 3D reconstruction.<n> UAVFF3D contains more than 170k real UAV images and more than 370k synthetic images rendered from high-quality textured 3D models.<n>It also includes a controlled HFOV-height test subset for diagnosing projection-geometry ambiguity.
• Score: 8.117428563545017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feed-forward 3D reconstruction has advanced rapidly, but current models remain unreliable in UAV photogrammetric acquisition. We argue that this failure is caused not only by appearance-domain shift, but also by UAV-specific camera-geometry variations, especially oblique views and HFOV-height ambiguity. Existing UAV datasets mainly emphasize scene diversity and provide limited coverage of camera configurations, which restricts robustness evaluation and UAV-domain adaptation. To address this gap, we introduce UAVFF3D, a geometry-aware real-synthetic benchmark for feed-forward UAV 3D reconstruction. UAVFF3D contains more than 170k real UAV images and more than 370k synthetic images rendered from high-quality textured 3D models, covering diverse HFOVs, flight altitudes, viewing directions, and acquisition patterns. It also includes a controlled HFOV-height test subset for diagnosing projection-geometry ambiguity. We further propose an evaluation protocol that jointly assesses camera-geometry estimation and dense scene reconstruction under a shared global alignment, avoiding the bias caused by separate camera and geometry alignments. Experiments on representative feed-forward reconstruction models show that UAVFF3D-based domain adaptation consistently improves camera and geometry estimation, reducing Ray Error by up to 84.2%, Pose ATE by up to 76.0%, and Chamfer Distance by up to 41.1%. In oblique scenes, adaptation reduces the oblique-nadir rotation gap by up to 90.7%. Under HFOV-height ambiguity, it improves robustness across HFOV-height configurations and yields more stable performance across HFOV settings. Incorporating camera priors further improves reconstruction under UAV-specific acquisition geometries. The dataset and evaluation code are available at https://github.com/yanxian-ll/UAVFF3D .

Related papers

• On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios [6.729903292561442]
  On-the-Fly3R is a training-free, progressive online 3D reconstruction framework for large-scale UAV images.<n>Our method enables reconstruction from unordered inputs via retrieval-guided dynamic subset construction.<n>Our method successfully scales various 3R models to over 5,000 images across square-kilometer UAV scenes.
  arXiv  Detail & Related papers  (2026-09-01T08:47:58Z)
• PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems [55.84012796735184]
  Poisoning input views of 3D reconstruction systems has been recently studied.<n>We propose PoInit-of-View, which optimize adversarial perturbations to intentionally introduce cross-view inconsistencies.<n> Experimental results demonstrate the effectiveness of our PoInit-of-View on diverse 3D reconstruction systems and datasets.
  arXiv  Detail & Related papers  (2026-04-17T00:48:12Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations [98.66466590444553]
  We propose Reliev3R, a weakly-supervised paradigm for training FFRMs from scratch without cost-prohibitive multi-view geometric annotations.<n>At the core of Reliev3R, we design an ambiguity-aware relative depth loss and a trigonometry-based reprojection loss to facilitate supervision for multi-view geometric consistency.
  arXiv  Detail & Related papers  (2026-04-01T06:46:54Z)
• Scale-Aware UAV-to-Satellite Cross-View Geo-Localization: A Semantic Geometric Approach [15.415356946083861]
  Cross-View Geo-Localization between UAV imagery and satellite images plays a crucial role in target localization and UAV self-positioning.<n>Most existing methods rely on the idealized assumption of scale consistency between UAV queries and satellite galleries.<n>This discrepancy leads to field-of-view misalignment and feature mismatch, significantly degrading CVGL robustness.<n>We propose a geometric framework that recovers the absolute metric scale from monocular UAV images using semantic anchors.
  arXiv  Detail & Related papers  (2026-03-08T08:51:19Z)
• An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks [17.58704237530163]
  3D computer vision algorithms continue to advance in handling sparse, unordered image sets.<n>Recently developed foundational models for 3D reconstruction have attracted attention due to their ability to handle very sparse image overlaps.<n>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.
  arXiv  Detail & Related papers  (2025-07-20T03:09:04Z)
• Evaluation of Flight Parameters in UAV-based 3D Reconstruction for Rooftop Infrastructure Assessment [0.08192907805418585]
  Rooftop 3D reconstruction using UAV-based photogrammetry offers a promising solution for infrastructure assessment.<n>Existing methods often require high percentages of image overlap and extended flight times to ensure model accuracy when using autonomous flight paths.<n>This study systematically evaluates key flight parameters-ground sampling distance (GSD) and image overlap-to optimize the 3D reconstruction of complex rooftop infrastructure.
  arXiv  Detail & Related papers  (2025-04-02T19:43:20Z)
• RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion [58.77329237533034]
  We propose a Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection.<n>RaCFormer achieves superior results of 64.9% mAP and 70.2% on nuScenes datasets.
  arXiv  Detail & Related papers  (2024-12-17T09:47:48Z)
• Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning [93.71280187657831]
  Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. We propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector.
  arXiv  Detail & Related papers  (2023-12-13T09:24:42Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis [99.06490355990354]
  We propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels. Our approach can considerably enhance model performance in sparse view conditions, achieving improvements of up to 94% in PSNR, in SSIM, and 31% in LPIPS.
  arXiv  Detail & Related papers  (2023-05-18T15:18:01Z)
• Enhanced Stable View Synthesis [86.69338893753886]
  We introduce an approach to enhance the novel view synthesis from images taken from a freely moving camera. The introduced approach focuses on outdoor scenes where recovering accurate geometric scaffold and camera pose is challenging.
  arXiv  Detail & Related papers  (2023-03-30T01:53:14Z)
• A volumetric change detection framework using UAV oblique photogrammetry - A case study of ultra-high-resolution monitoring of progressive building collapse [4.001160460535953]
  We present a case study that performs an unmanned aerial vehicle based fine-scale 3D change detection and monitoring 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. We propose a hierarchical change detection framework that unifies multi-temporal UAV images for pose estimation, reconstruction, and a coarse-to-fine 3D density change analysis.
  arXiv  Detail & Related papers  (2021-08-05T18:20:29Z)
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry [57.5549733585324]
  D3VO is a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. We model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-03-02T17:47:13Z)

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.