R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections

• URL: http://arxiv.org/abs/2505.15294v1
• Date: Wed, 21 May 2025 09:25:22 GMT
• Title: R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections
• Authors: Xu yan, Zhaohui Wang, Rong Wei, Jingbo Yu, Dong Li, Xiangde Liu,
• Abstract summary: R3GS is a robust reconstruction and relocalization framework tailored for unconstrained datasets.<n>To mitigate the adverse effects of transient objects on the reconstruction process, we ffne-tune a lightweight human detection network.<n>To address the challenges posed by sky regions in outdoor scenes, we propose an effective sky-handling technique that incorporates a depth prior as a constraint.
• Score: 9.633163304379861
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network (CNN) with a local feature encoded by the multiresolution hash grids [2]. Subsequently, several shallow multi-layer perceptrons (MLPs) predict the attributes of each Gaussians, including color, opacity, and covariance. To mitigate the adverse effects of transient objects on the reconstruction process, we ffne-tune a lightweight human detection network. Once ffne-tuned, this network generates a visibility map that efffciently generalizes to other transient objects (such as posters, banners, and cars) with minimal need for further adaptation. Additionally, to address the challenges posed by sky regions in outdoor scenes, we propose an effective sky-handling technique that incorporates a depth prior as a constraint. This allows the inffnitely distant sky to be represented on the surface of a large-radius sky sphere, signiffcantly reducing ffoaters caused by errors in sky reconstruction. Furthermore, we introduce a novel relocalization method that remains robust to changes in lighting conditions while estimating the camera pose of a given image within the reconstructed 3DGS scene. As a result, R3GS significantly enhances rendering ffdelity, improves both training and rendering efffciency, and reduces storage requirements. Our method achieves state-of-the-art performance compared to baseline methods on in-the-wild datasets. The code will be made open-source following the acceptance of the paper.

Related papers

• HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis [59.25751939710903]
  We propose a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos.<n>Our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately.<n>Results highlight a practical and scalable solution for EVS in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-24T03:54:40Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications.<n>Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas.<n>We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• DehazeGS: Seeing Through Fog with 3D Gaussian Splatting [17.119969983512533]
  We introduce DehazeGS, a method capable of decomposing and rendering a fog-free background from participating media.<n>Experiments on both synthetic and real-world foggy datasets demonstrate that DehazeGS achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-01-07T09:47:46Z)
• DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes [81.56206845824572]
  Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. Few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.
  arXiv  Detail & Related papers  (2024-11-19T07:51:44Z)
• GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstruction [1.7624442706463355]
  This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) For tackling the scalability issue, we split the large scene into multiple cells, and the candidate point-cloud and camera views of each cell are correlated. We show that our method consistently generates more high-fidelity rendering results than state-of-the-art methods of large-scale scene reconstruction.
  arXiv  Detail & Related papers  (2024-09-19T13:43:31Z)
• Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections [12.807052947367692]
  Photometric variation and transient occluders in unconstrained images make it difficult to reconstruct the original scene accurately. Previous approaches tackle the problem by introducing a global appearance feature in Neural Radiance Fields (NeRF) Inspired by this fact, we propose Gaussian in the wild (GS-W), a method that uses 3D Gaussian points to reconstruct the scene.
  arXiv  Detail & Related papers  (2024-03-23T03:55:41Z)
• AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation [51.143540967290114]
  We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth computation and estimation. This is achieved by reversing, or undo''-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame.
  arXiv  Detail & Related papers  (2023-10-15T05:15:45Z)
• NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction [50.54946139497575]
  We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We demonstrate that NeRFusion achieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.
  arXiv  Detail & Related papers  (2022-03-21T18:56:35Z)
• InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering [55.70938412352287]
  We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints. We achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.
  arXiv  Detail & Related papers  (2021-12-31T11:56:01Z)
• PERF: Performant, Explicit Radiance Fields [1.933681537640272]
  We present a novel way of approaching image-based 3D reconstruction based on radiance fields. The problem of volumetric reconstruction is formulated as a non-linear least-squares problem and solved explicitly without the use of neural networks.
  arXiv  Detail & Related papers  (2021-12-10T15:29:00Z)

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.