SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes

• URL: http://arxiv.org/abs/2511.18290v1
• Date: Sun, 23 Nov 2025 05:03:49 GMT
• Title: SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
• Abstract summary: 3D reconstruction in large-scale scenes is a fundamental task in 3D perception.<n>Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times.<n>We propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction.
• Score: 30.52500975808177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches.

Related papers

• EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams [108.45551580182384]
  EvTrajGS is an accurate and efficient 3D Gaussian Splatting framework for unposed event streams.<n>Our method enables reliable joint pose-scene optimization from coarse pose priors, eliminating the need for computationally expensive SLAM-style pipelines.
  arXiv  Detail & Related papers  (2026-08-09T09:00:30Z)
• Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction [50.5449251266956]
  This paper addresses the task of large-scale 3D scene reconstruction from long video sequences.<n>Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D priors or geometric constraints.<n>We propose a novel neural global context representation that efficiently compresses and retains long-range scene information.
  arXiv  Detail & Related papers  (2026-04-09T17:59:50Z)
• SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction [36.282461368600806]
  SwiftNDC is a fast and general framework built around a Neural Depth Correction field.<n>We generate a dense point cloud through back-projection and robust reprojection-error filtering.<n>This reliable dense geometry substantially accelerates 3D Gaussian Splatting (3DGS) for mesh reconstruction.<n>We conduct a comprehensive study across five datasets, including two for mesh reconstruction, as well as three for novel-view synthesis.
  arXiv  Detail & Related papers  (2026-02-26T03:07:53Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction [8.905668938519279]
  3D Gaussian representations have significantly improved the quality and efficiency of image-based scene reconstruction.<n>Many existing methods rely on approximate depth estimates and global sortings, which can introduce artifacts and limit the fidelity of the reconstructed mesh.<n>We present Sorted Opacity Fields (SOF), a method designed to recover detailed surfaces from 3D Gaussians with both speed and precision.
  arXiv  Detail & Related papers  (2025-06-23T21:20:52Z)
• QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization [69.50126552763157]
  Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more.<n>Existing approaches based on rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model textureless regions.<n>We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes.
  arXiv  Detail & Related papers  (2025-05-08T18:43:26Z)
• Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields [20.363006625978787]
  We present a method to reconstruct dynamic scenes from monocular continuous-wave timeof-flight (C-ToF) cameras.<n>The method achieves similar or better accuracy than neural approaches and is 100x faster.
  arXiv  Detail & Related papers  (2025-05-08T15:45:53Z)
• FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [50.534213038479926]
  FreeSplat++ is an alternative approach to large-scale indoor whole-scene reconstruction.<n>Our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.
  arXiv  Detail & Related papers  (2025-03-29T06:22:08Z)
• 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)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)

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.