Large-scale visual SLAM for in-the-wild videos

• URL: http://arxiv.org/abs/2504.20496v1
• Date: Tue, 29 Apr 2025 07:37:51 GMT
• Title: Large-scale visual SLAM for in-the-wild videos
• Authors: Shuo Sun, Torsten Sattler, Malcolm Mielle, Achim J. Lilienthal, Martin Magnusson,
• Abstract summary: We introduce a robust pipeline designed to improve 3D reconstruction from casual videos.<n>We build upon recent deep visual odometry methods but increase robustness in several ways.<n>We demonstrate large-scale contiguous 3D models from several online videos in various environments.
• Score: 28.58692815339531
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and robust 3D scene reconstruction from casual, in-the-wild videos can significantly simplify robot deployment to new environments. However, reliable camera pose estimation and scene reconstruction from such unconstrained videos remains an open challenge. Existing visual-only SLAM methods perform well on benchmark datasets but struggle with real-world footage which often exhibits uncontrolled motion including rapid rotations and pure forward movements, textureless regions, and dynamic objects. We analyze the limitations of current methods and introduce a robust pipeline designed to improve 3D reconstruction from casual videos. We build upon recent deep visual odometry methods but increase robustness in several ways. Camera intrinsics are automatically recovered from the first few frames using structure-from-motion. Dynamic objects and less-constrained areas are masked with a predictive model. Additionally, we leverage monocular depth estimates to regularize bundle adjustment, mitigating errors in low-parallax situations. Finally, we integrate place recognition and loop closure to reduce long-term drift and refine both intrinsics and pose estimates through global bundle adjustment. We demonstrate large-scale contiguous 3D models from several online videos in various environments. In contrast, baseline methods typically produce locally inconsistent results at several points, producing separate segments or distorted maps. In lieu of ground-truth pose data, we evaluate map consistency, execution time and visual accuracy of re-rendered NeRF models. Our proposed system establishes a new baseline for visual reconstruction from casual uncontrolled videos found online, demonstrating more consistent reconstructions over longer sequences of in-the-wild videos than previously achieved.

Related papers

• Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction [78.27956235915622]
  Traditional SLAM systems struggle with highly dynamic scenes commonly found in casual videos.<n>This work leverages a 3D point tracker to separate the camera-induced motion from the observed motion of dynamic objects.<n>Our framework combines the core of traditional SLAM -- bundle adjustment -- with a robust learning-based 3D tracker front-end.
  arXiv  Detail & Related papers  (2025-04-20T07:29:42Z)
• VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment [63.21396416244634]
  VideoLifter is a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis.<n>It significantly accelerates the reconstruction process, reducing training time by over 82% while holding better visual quality than current SOTA methods.
  arXiv  Detail & Related papers  (2025-01-03T18:52:36Z)
• Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors [5.407319151576265]
  We introduce a generative approach for pose-free (without camera parameters) reconstruction of 360 scenes from a sparse set of 2D images.<n>We propose an image-to-image generative model designed to inpaint missing details and remove artifacts in novel view renders and depth maps of a 3D scene.
  arXiv  Detail & Related papers  (2024-11-24T19:34:58Z)
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes [75.9110646062442]
  We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.
  arXiv  Detail & Related papers  (2023-08-16T09:50:35Z)
• 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)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)
• Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth [90.33296913575818]
  In some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency. We propose a locally weighted linear regression method to recover the scale and shift with very sparse anchor points. Our method can boost the performance of existing state-of-the-art approaches by 50% at most over several zero-shot benchmarks.
  arXiv  Detail & Related papers  (2022-02-03T08:52:54Z)
• Towards Non-Line-of-Sight Photography [48.491977359971855]
  Non-line-of-sight (NLOS) imaging is based on capturing the multi-bounce indirect reflections from the hidden objects. Active NLOS imaging systems rely on the capture of the time of flight of light through the scene. We propose a new problem formulation, called NLOS photography, to specifically address this deficiency.
  arXiv  Detail & Related papers  (2021-09-16T08:07:13Z)
• Learning monocular 3D reconstruction of articulated categories from motion [39.811816510186475]
  Video self-supervision forces the consistency of consecutive 3D reconstructions by a motion-based cycle loss. We introduce an interpretable model of 3D template deformations that controls a 3D surface through the displacement of a small number of local, learnable handles. We obtain state-of-the-art reconstructions with diverse shapes, viewpoints and textures for multiple articulated object categories.
  arXiv  Detail & Related papers  (2021-03-30T13:50:27Z)

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.