Detailed Real-Time Urban 3D Reconstruction from Video

By Marc Pollefeys, David Nistér, Jan-Michael Frahm, Amir Akbarzadeh, Philippos Mordohai, Brian Clipp, C. Engels, David Gallup, Seon Joo Kim, Paul C. Merrell and 9 more. 2007

857 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].”
A Survey on Structure from Motion (2017, neutral): “For additional reading on urban scene reconstruction, we refer the reader, e.g., to [51, 56] and the references therein.”
Tanks and temples (2017, background): “While a number of projects have considered 3D reconstruction from video [Frahm et al. 2010; Kolev et al. 2014; New-combe et al. 2011; Pollefeys et al. 2008; Schöps et al. 2015; Tanskanen et al. 2013; Vogiatzis and Hernández 2011; Wendel et al. 2012], much more work in the literature is devoted to…”
Toward automated driving in cities using close-to-market sensors: An overview of the V-Charge Project (2013, methodology): “For now, we first extract perspective images out of the fisheye images and subsequently run plane sweep stereo matching [14] to get depth maps.”
Block-NeRF: Scalable Large Scene Neural View Synthesis (2022, methodology): “Researchers have been developing and reﬁning techniques for 3D reconstruction from large image collections for decades [1,16,33,47,57,77], and much current work relies on mature and robust software implementations such as COLMAP to perform this task [55].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Pollefeys (2008) propose a large scale, realtime 3D reconstruction system based on depth map representation.”
Building Rome on a Cloudless Day (2010, background): “The proposed system brings the computation of models from Internet photo collections on par with state-of-theart performance for reconstruction from video [6] by extending the capabilities of each step of the reconstruction pipeline to efficiently handle the variability and complexity of large-scale”
Elastic Fragments for Dense Scene Reconstruction (2013, background): “Substantial progress on dense scene reconstruction from photographs and video sequences has been made, despite the ambiguity of photometric cues [20] [26] [21] [6] [15] [17].”
Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation (2012, methodology): “mann, 2010) or MVS imagery (Chauve et al., 2010). Such data have spatially heterogeneous point distributions without induced neighborhood relationships between the points, and contain outliers, especially when generated from MVS imagery. Vosselman et al. (2005) present a semi-automatic approach usin”
Automatic Creation of Semantically Rich 3D Building Models from Laser Scanner Data (2011, methodology): “used video to model urban environments from a moving vehicle (Pollefeys et al., 2008).”
Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera (2011, neutral): “[31]).”