The structure-from-motion reconstruction pipeline - a survey with focus on short image sequences
By Klaus Häming, Gabriele Peters. 2010
88 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Jitendra Malik
- Luc Van Gool
- Andrea Vedaldi
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Li Fei-Fei
- Trevor Darrell
In 3D Vision & Pose
- Leonidas J. Guibas
- Hao Su
- Silvio Savarese
- Andreas Geiger
- Christopher Bongsoo Choy
- Anders P. Eriksson
- Jhony Kaesemodel Pontes
- Jitendra Malik
Citations in the corpus
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image (2016, background): “3D reconstruction from single images While most researches focus on multi-view geometry such as SFM and SLAM [11, 10], ideally, one expect that 3D can be reconstructed from the abundant single-view images.”
- Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, background): “Existing 3D reconstruction methods can be divided into two broad categories: reconstruction from a single image [5], and from multiple images ( e.g . structure from motion [14]).”
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, background): “ions stem from a number of key technical assumptions. One typical assumption is that features can be matched across views [3,4,5,6] as hypothesized by the majority of the methods based on SFM or SLAM [7,8]. It has been demonstrated (for instance see [9]) that if the viewpoints are separated by a lar”
- Weakly Supervised 3D Reconstruction with Adversarial Constraint (2017, methodology): “This problem has been explored by a large body of work in computer vision, within domains such as structure from motion [18, 12] or multiview stereo [13, 14, 16, 19].”
- Implicit Surface Representations As Layers in Neural Networks (2019, background): “As a research field, 3D understanding & reconstruction has achieved great progress trying to tackle many categories of problems such as structure from motion [14], multi-view Figure 1.”