Visual Modeling with a Hand-Held Camera

By Marc Pollefeys, Luc Van Gool, M. Vergauwen, F. Verbiest, K. Cornelis, J. Tops, Reinhard Koch. 2004

1,081 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning a Multi-View Stereo Machine (2017, background): “Another approach to MVS involves representing the reconstruction as a collection of depth maps [6, 57, 41, 13, 40].”
Consistent Depth Maps Recovery from a Video Sequence (2009, background): “However, even with oversegmentation or soft segmentation, accurate disparity estimate is still difficult to obtain especially in the textured regions and along the segment boundaries.”
Make3D: Learning 3D Scene Structure from a Single Still Image (2009, methodology): “Given a sparse set of images of a scene, it is sometimes possible to construct a 3-d model using techniques such as structure from motion (SFM) [5], [32], which start by taking two or more photographs, then ﬁnd correspondences between the images, and ﬁnally use triangulation to obtain 3-d locations…”
State of research in automatic as-built modelling (2015, background): “Consisting, basically, of a set of 3D points endowed with 3D Cartesian coordinates and possibly colour information, these models that will be denoted from now on as point clouds, are useful for visualisation or augmented reality purposes [90,91,1,94].”
Understanding Transit Scenes: A Survey on Human Behavior-Recognition Algorithms (2010, methodology): “Recent developments include 3-D environmental modeling reconstructed using the shape-from-motion technique [36] and 3-D imagery”
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting (2024, methodology): “To address this task, various traditional methods have been proposed, including structure-from-motion (SfM) [1, 48, 50, 56] for sparse reconstruction and calibration, and multi-view stereo (MVS) [23,47,52] for dense reconstruction.”
Structure-from-Motion Revisited (2016, background): “The early self-calibrating metric reconstruction systems [42, 6, 19, 16, 46] served as the foundation for the first systems on unordered Internet photo collections [47, 53] and urban scenes [45].”
GPU-based Video Feature Tracking And Matching (2006, background): “While certain sequential tasks like structure from motion for video [3] require online feature point tracking, others need features to be extracted and matched across frames separated in time (eg.”
Picking the best DAISY (2009, background): “When combined with interest points [11, 12], it facilitates point matching without initialization for image stitching and structure from motion [3, 16, 19].”
StereoScan: Dense 3d reconstruction in real-time (2011, methodology): “3d reconstruction from uncalibrated image collections has been shown by Koch [17], Pollefeys [22], Seitz [24] et al , [9], [10].”
Multiview Imaging and 3DTV (2007, background): “When the scene itself contains a lot of interest points, it is possible to extract and match feature points directly for camera calibration (known as structure from motion in computer vision), such as the work in [26].”
The structure-from-motion reconstruction pipeline - a survey with focus on short image sequences (2010, background): “publications these systems and their improvements are covered [3, 14, 15, 21, 22, 23, 30, 33, 34, 38, 42, 46].”
A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization (2012, background): “To resolve this ambiguity, Xiao et al. suggested to add extraneous “basis constraints” so as to make the system well-constrained.”
On benchmarking camera calibration and multi-view stereo for high resolution imagery (2008, background): “Various authors propose a so called structure and motion pipeline [2, 12, 13, 14, 17, 21, 22].”
Multi-View Stereo Revisited (2006, positive): “While there is a large body of prior work on multi-view stereo algorithms, the three papers that are most closely related are Narayanan et al.'s Virtualized Reality technique [9], Pollefeys et al's' visual modeling system [11] [12], and the multi-stereo approach of Hernández and Schmitt [6] [7].”
Consistent Generative Query Networks (2018, background): “This type of algorithms include structure-from-motion, structure-from-depth and multi view geometry techniques and while these models have achieved impressive results, they require researchers to handcraft a feature space in advance (Pollefeys et al., 2004; Wu et al., 2016; Zhang et al., 2015).”