Reducing Drift in Structure From Motion Using Extended Features

• URL: http://arxiv.org/abs/2008.12295v3
• Date: Wed, 14 Oct 2020 01:59:53 GMT
• Title: Reducing Drift in Structure From Motion Using Extended Features
• Abstract summary: Low-frequency long-range errors (drift) are an endemic problem in 3D structure from motion. We present a method to dramatically reduce scale and positional drift by using extended structural features such as planes and vanishing points.
• Score: 82.37566035407689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-frequency long-range errors (drift) are an endemic problem in 3D structure from motion, and can often hamper reasonable reconstructions of the scene. In this paper, we present a method to dramatically reduce scale and positional drift by using extended structural features such as planes and vanishing points. Unlike traditional feature matches, our extended features are able to span non-overlapping input images, and hence provide long-range constraints on the scale and shape of the reconstruction. We add these features as additional constraints to a state-of-the-art global structure from motion algorithm and demonstrate that the added constraints enable the reconstruction of particularly drift-prone sequences such as long, low field-of-view videos without inertial measurements. Additionally, we provide an analysis of the drift-reducing capabilities of these constraints by evaluating on a synthetic dataset. Our structural features are able to significantly reduce drift for scenes that contain long-spanning man-made structures, such as aligned rows of windows or planar building facades.

Related papers

• Global Structure-from-Motion Meets Feedforward Reconstruction [50.69771349993019]
  Structure-from-Motion is a central challenge in computer vision.<n>Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods.<n>We propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods.
  arXiv  Detail & Related papers  (2026-05-25T17:58:03Z)
• 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)
• AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model [29.087865646035695]
  Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction.<n>We propose AnyRecon, a scalable framework for reconstruction from arbitrary and unordered sparse inputs.<n>Experiments demonstrate robust and scalable reconstruction across irregular inputs, large viewpoint gaps, and long trajectories.
  arXiv  Detail & Related papers  (2026-04-21T17:59:47Z)
• Static Scene Reconstruction from Dynamic Egocentric Videos [0.08594140167290099]
  Egocentric videos present unique challenges for 3D reconstruction due to rapid camera motion and frequent dynamic interactions.<n>We propose a robust pipeline that adapts static reconstruction backbones to long-form egocentric video.
  arXiv  Detail & Related papers  (2026-03-23T18:19:46Z)
• PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences [6.455635287305678]
  PAS3R is a pose-adaptive streaming reconstruction framework that dynamically modulates state updates according to camera motion and scene structure.<n>We show that PAS3R significantly improves trajectory accuracy, depth estimation, and point cloud reconstruction quality in long video sequences.
  arXiv  Detail & Related papers  (2026-03-22T22:57:30Z)
• Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change [52.46888249268445]
  Long-term environmental monitoring requires the ability to reconstruct and align 3D models across repeated site visits separated by months or years.<n>Existing approaches rely on post-hoc alignment of independently reconstructed sessions.<n>We propose enforcing cross-session correspondences directly within a joint SfM reconstruction.
  arXiv  Detail & Related papers  (2026-02-24T06:12:51Z)
• StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval [75.28673512571449]
  A key challenge in Continual Text-to-Video Retrieval is feature drift.<n>We propose StructAlign, a structured cross-modal alignment method for CTVR.<n>Our method consistently outperforms state-of-the-art continual retrieval approaches.
  arXiv  Detail & Related papers  (2026-01-28T13:34:44Z)
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention [54.15345846343084]
  We propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality.<n>Part Attention is a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions.<n>Experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.
  arXiv  Detail & Related papers  (2025-07-23T17:57:16Z)
• HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene [11.906835503107189]
  We propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation.<n>We show that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.
  arXiv  Detail & Related papers  (2025-06-11T08:45:08Z)
• Structure from Collision [20.586692311724914]
  A new task called Structure from Collision (SfC) aims to estimate the structure (including the invisible internal structure) of an object from appearance changes during collision.<n>We propose a novel model called SfC-NeRF that optimize the invisible internal structure of an object through a video sequence under physical, appearance (i.e., visible external structure) and neural constraints.<n>Experiments on 115 objects involving diverse structures revealed the properties of SfC and demonstrated the effectiveness of the proposed SfC-NeRF.
  arXiv  Detail & Related papers  (2025-05-27T15:30:01Z)
• SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations [44.53106180688135]
  This work takes on the challenge of reconstructing 3D scenes from sparse or single-view inputs.<n>We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations.<n>Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency.
  arXiv  Detail & Related papers  (2025-05-17T13:05:13Z)
• Large-scale visual SLAM for in-the-wild videos [28.58692815339531]
  We 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. We demonstrate large-scale contiguous 3D models from several online videos in various environments.
  arXiv  Detail & Related papers  (2025-04-29T07:37:51Z)
• BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation [54.12899218104669]
  3D scenes have highly complex structures and need to ensure that the output is dense, coherent, and contains all necessary structures.<n>Current 3D scene generation methods rely on pre-trained text-to-image diffusion models and monocular depth estimators.<n>We propose BloomScene, a lightweight structured 3D Gaussian splatting for crossmodal scene generation.
  arXiv  Detail & Related papers  (2025-01-15T11:33:34Z)
• CoStruction: Conjoint radiance field optimization for urban scene reconStruction with limited image overlap [2.946747492685909]
  CoStruction is a novel hybrid implicit surface reconstruction method tailored for large driving sequences with limited camera overlap. Our method performs joint optimization of both radiance fields in addition to guided sampling achieving accurate reconstruction of large areas along with fine structures in complex urban scenarios.
  arXiv  Detail & Related papers  (2025-01-07T16:48:47Z)
• 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. 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)
• Robust Incremental Structure-from-Motion with Hybrid Features [73.55745864762703]
  We introduce an incremental Structure-from-Motion (SfM) system that leverages lines and their structured geometric relations. Our system is consistently more robust and accurate compared to the widely used point-based state of the art in SfM.
  arXiv  Detail & Related papers  (2024-09-29T22:20:32Z)
• Simultaneous Map and Object Reconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. We take inspiration from recent novel view synthesis methods and pose the reconstruction problem as a global optimization. By careful modeling of continuous-time motion, our reconstructions can compensate for the rolling shutter effects of rotating LiDAR sensors.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation [12.564019188842861]
  We show analytically that as the representation power of the network increases, the optimization approaches a partial differential equation (PDE) in the continuum limit that is unstable. We show that this instability can manifest in existing network optimization, leading to irregularities in the reconstructed surface and/or convergence to sub-optimal local minima. We introduce a new regularization term that still counteracts the eikonal instability but without over-regularizing.
  arXiv  Detail & Related papers  (2023-05-28T18:27:15Z)
• BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling [43.246536947828844]
  We propose a framework that factorizes time and space by formulating a scene as a composition of bandlimited, high-dimensional signals. We demonstrate compelling results across complex dynamic scenes that involve changes in lighting, texture and long-range dynamics.
  arXiv  Detail & Related papers  (2023-02-27T06:40:32Z)
• Enforcing connectivity of 3D linear structures using their 2D projections [54.0598511446694]
  We propose to improve the 3D connectivity of our results by minimizing a sum of topology-aware losses on their 2D projections. This suffices to increase the accuracy and to reduce the annotation effort required to provide the required annotated training data.
  arXiv  Detail & Related papers  (2022-07-14T11:42:18Z)
• Coarse to Fine Multi-Resolution Temporal Convolutional Network [25.08516972520265]
  We propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation. The decoder follows a coarse-to-fine structure with an implicit ensemble of multiple temporal resolutions. Experiments show that our stand-alone architecture, together with our novel feature-augmentation strategy and new loss, outperforms the state-of-the-art on three temporal video segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-05-23T06:07:40Z)
• Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video [90.93141123721713]
  Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera.
  arXiv  Detail & Related papers  (2020-05-07T10:39:20Z)

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.