Corpus ID: 220713313

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

@article{Tankovich2020HITNetHI,
  title={HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching},
  author={V. Tankovich and Christian H{\"a}ne and S. Fanello and Yinda Zhang and S. Izadi and Sofien Bouaziz},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.12140}
}
This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses. To achieve a high level of accuracy, our network not only geometrically reasons… Expand
PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

References

SHOWING 1-10 OF 57 REFERENCES
Hierarchical Deep Stereo Matching on High-Resolution Images
Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures
Real-Time Stereo Matching Network with High Accuracy
Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
  • Amit Shaked, Lior Wolf
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection
StereoDRNet: Dilated Residual StereoNet
Pyramid Stereo Matching Network
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Learning Efficient Stereo Matching Network With Depth Discontinuity Aware Super-Resolution
...
1
2
3
4
5
...