Multi-resolution real-time stereo on commodity graphics hardware

By Ruigang Yang, Marc Pollefeys. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003

344 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/77f8b164fafa40ede99e33902a4264c7fc8e6b85

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

Citations in the corpus

Multi-View Stereo: A Tutorial (2015, background): “Some measures such as SAD or SSD are extremely fast to compute and easily adapted to specialized hardware such as GPUs [202, 101, 76, 142, 145].”
Fast cost-volume filtering for visual correspondence and beyond (2011, neutral): “[45].”
Building Rome on a Cloudless Day (2010, methodology): “Our proposed method uses an extended version of Yang and Pollefeys stereo [7] combined with novel multi-layer depthmap fusion [8].”
Locally adapted hierarchical basis preconditioning (2006, background): “GPUs ( Yang and Pollefeys 2003, Bolz et al. 2003).”
Segment based 3D object shape priors (2015, methodology): “As an input to our formulation we computed depth maps using plane sweeping stereo matching [24] for each of the images.”
Visual-inertial navigation, mapping and localization: A scalable real-time causal approach (2011, background): “This problem is sometimes referred to as ‘odometry’ or ‘navigation’ in different contexts.”
Real-Time Direct Dense Matching on Fisheye Images Using Plane-Sweeping Stereo (2014, methodology): “In addition to the ease of matching images taken from arbitrary configurations, the plane-sweeping algorithm has the advantage of real-time performance which can be achieved by utilizing the texturing capabilities of GPUs [22, 6].”
A Survey of Urban Reconstruction (2013, methodology): “Plane sweeping has been successfully utilized for the recovery of dense structure and was consecutively extended to utilize programmable graphics hardware [YP03] and multiple sweeping directions [GFM ∗ 07].”
GPU-based Video Feature Tracking And Matching (2006, methodology): “The increasing programmability and computational power of the graphics processing unit (GPU) present in modern graphics hardware provides great scope for acceleration of computer vision algorithms which can be parallelized [3, 11,12,14,15,16,17].”
A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration (2007, methodology): “We use GPU-accelerated space-sweep and dynamic programming methods (see [33, 11, 35, 36]) to obtain the depth maps used as input for our range image integration approach.”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, positive): “Since the choice of an appropriate matching window size is difficult, multilevel matching is used, and the matching criterion is the sum of normalized cross correlations (NCC) for several fixed window sizes 3 (or scale (cid:4) ) as in [67].”
Detailed Real-Time Urban 3D Reconstruction from Video (2007, methodology): “Plane sweeping stereo was selected because it is ideal for efficient implementation due to its simplicity and parallelizability [12, 67].”