Splat and Replace: 3D Reconstruction with Repetitive Elements

• URL: http://arxiv.org/abs/2506.06462v1
• Date: Fri, 06 Jun 2025 18:34:22 GMT
• Title: Splat and Replace: 3D Reconstruction with Repetitive Elements
• Abstract summary: We leverage repetitive elements in 3D scenes to improve novel view synthesis.<n>Our key observation is that our environment is often full of repetitive elements.<n>We propose a method that segments each repeated instance in a 3DGS reconstruction, registers them together, and allows information to be shared among instances.
• Score: 15.648876467553544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthesis but renderings of unseen and occluded parts remain low-quality if the training views are not exhaustive enough. Our key observation is that our environment is often full of repetitive elements. We propose to leverage those repetitions to improve the reconstruction of low-quality parts of the scene due to poor coverage and occlusions. We propose a method that segments each repeated instance in a 3DGS reconstruction, registers them together, and allows information to be shared among instances. Our method improves the geometry while also accounting for appearance variations across instances. We demonstrate our method on a variety of synthetic and real scenes with typical repetitive elements, leading to a substantial improvement in the quality of novel view synthesis.

Related papers

• TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views [5.274411980510585]
  We introduce a new class of 3D losses that do not rely on rendering and can be combined with essentially all losses previously reported in the literature.<n>Our method is easy to integrate with a diverse set of backbones, and our experiments on the DTU and Tanks-and-Temples datasets demonstrate that TV-SGS improves the geometry of the outputs compared to the backbone.
  arXiv  Detail & Related papers  (2026-09-07T16:40:51Z)
• DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images [22.61939963916488]
  Novel view synthesis (NVS) is a fundamental problem in computer vision and graphics.<n>Recent advances in neural radiance fields (NeRF), 3D Gaussian Splatting (3DGS), and generative view synthesis have substantially improved its quality.<n>We propose DeNVS, a novel framework for high-fidelity novel views directly from sparse motion-blurred images.
  arXiv  Detail & Related papers  (2026-05-31T16:04:55Z)
• VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors [79.88300861391114]
  VidSplat is a training-free generative reconstruction framework.<n>We tackle two key challenges that enable the effective integration of generation and reconstruction.<n>Experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.
  arXiv  Detail & Related papers  (2026-05-12T02:20:31Z)
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
  We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
  arXiv  Detail & Related papers  (2025-08-05T04:50:29Z)
• Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views [29.85363432402896]
  We propose a novel neural rendering framework to accomplish the unposed and extremely sparse-view 3D reconstruction in unbounded 360deg scenes.<n>By employing a dense stereo reconstruction model to recover coarse geometry, we introduce a layer-specific bootstrap optimization to refine the noise and fill occluded regions in the reconstruction.<n>Our approach outperforms existing state-of-the-art methods in terms of rendering quality and surface reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-03-31T17:59:25Z)
• Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View [5.222115919729418]
  Single-view 3D reconstruction is currently approached from two dominant perspectives.<n>We propose a hybrid method following a divide-and-conquer strategy.<n>We demonstrate the reconstruction performance of our approach on both synthetic and real-world scenes.
  arXiv  Detail & Related papers  (2024-04-04T12:58:46Z)
• Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction [51.3632308129838]
  We present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing.
  arXiv  Detail & Related papers  (2024-03-28T11:12:33Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• ReconFusion: 3D Reconstruction with Diffusion Priors [104.73604630145847]
  We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions.
  arXiv  Detail & Related papers  (2023-12-05T18:59:58Z)
• Learning to Render Novel Views from Wide-Baseline Stereo Pairs [26.528667940013598]
  We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. Existing approaches to novel view synthesis from sparse observations fail due to recovering incorrect 3D geometry. We propose an efficient, image-space epipolar line sampling scheme to assemble image features for a target ray.
  arXiv  Detail & Related papers  (2023-04-17T17:40:52Z)
• VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction [64.09702079593372]
  VolRecon is a novel generalizable implicit reconstruction method with Signed Ray Distance Function (SRDF) On DTU dataset, VolRecon outperforms SparseNeuS by about 30% in sparse view reconstruction and achieves comparable accuracy as MVSNet in full view reconstruction.
  arXiv  Detail & Related papers  (2022-12-15T18:59:54Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• Fast and Explicit Neural View Synthesis [17.811091108978463]
  We study the problem of novel view synthesis of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuous nor implicit. Our model is trained in a category-agnostic manner and does not require scene-specific optimization.
  arXiv  Detail & Related papers  (2021-07-12T23:24:53Z)

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.