DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery

• URL: http://arxiv.org/abs/2503.16964v1
• Date: Fri, 21 Mar 2025 09:21:43 GMT
• Title: DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
• Authors: Jiadong Tang, Yu Gao, Dianyi Yang, Liqi Yan, Yufeng Yue, Yi Yang,
• Abstract summary: DroneSplat is a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery.<n>Our method adaptively adjusts masking thresholds by integrating local-global segmentations with statistical approaches.<n>For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes.
• Score: 20.869325438718676
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

Related papers

• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction [59.77970844874235]
  We present FreeSplatter, a feed-forward reconstruction framework capable of generating high-quality 3D Gaussians from sparse-view images.<n>FreeSplatter is built upon a streamlined transformer architecture, comprising sequential self-attention blocks.<n>We show FreeSplatter's potential in enhancing the productivity of downstream applications, such as text/image-to-3D content creation.
  arXiv  Detail & Related papers  (2024-12-12T18:52:53Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction [24.33543853742041]
  3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method. We propose an optimization strategy that effectively regularizes splat features by modeling them as the outputs of a corresponding implicit neural field. Our approach effectively handles static and dynamic cases, as demonstrated by extensive testing across different setups and scene complexities.
  arXiv  Detail & Related papers  (2024-09-17T14:04:20Z)
• EaDeblur-GS: Event assisted 3D Deblur Reconstruction with Gaussian Splatting [8.842593320829785]
  Event-assisted 3D Deblur Reconstruction with Gaussian Splatting (EaDeblur-GS) is presented. It integrates event camera data to enhance the robustness of 3DGS against motion blur. It achieves sharp 3D reconstructions in real-time, demonstrating performance comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-18T13:55:54Z)
• WildGaussians: 3D Gaussian Splatting in the Wild [80.5209105383932]
  We introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data.
  arXiv  Detail & Related papers  (2024-07-11T12:41:32Z)
• SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting [44.42317312908314]
  3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds. Current methods require highly controlled environments to meet the inter-view consistency assumption of 3DGS. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors.
  arXiv  Detail & Related papers  (2024-06-28T17:07:11Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments [77.0399450848749]
  We propose an OccNeRF method for training occupancy networks without 3D supervision. We parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. For semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model.
  arXiv  Detail & Related papers  (2023-12-14T18:58:52Z)
• Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Survey [11.176205645608865]
  We propose the Drone-NeRF framework to enhance the efficient reconstruction of large-scale drone photography scenes. Our approach involves dividing the scene into uniform sub-blocks based on camera position and depth visibility. Sub-scenes are trained in parallel using NeRF, then merged for a complete scene.
  arXiv  Detail & Related papers  (2023-08-30T03:17:57Z)
• DroNeRF: Real-time Multi-agent Drone Pose Optimization for Computing Neural Radiance Fields [19.582873794287632]
  We present a novel optimization algorithm called DroNeRF for the autonomous positioning of monocular camera drones around an object. NeRF is a novel view synthesis technique used to generate new views of an object or scene from a set of input images.
  arXiv  Detail & Related papers  (2023-03-08T01:46:19Z)

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.