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

By Vladimir Tankovich, Christian Häne, Sean Ryan Fanello, Yinda Zhang, Shahram Izadi, Sofien Bouaziz. Computer Vision and Pattern Recognition, 2020

299 citations recorded by the source corpus.

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 about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations. Our architecture is inherently multi-resolution allowing the propagation of information across different levels. Multiple experiments prove the effectiveness of the proposed approach at a fraction of the computation required by state-of-the-art methods. At the time of writing, HITNet ranks 1st-3rd on all the metrics published on the ETH3D website for two view stereo, ranks 1st on most of the metrics amongst all the end-to-end learning approaches on Middlebury-v3, ranks 1st on the popular KITTI 2012 and 2015 benchmarks among the published methods faster than 100 ms.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/da7ee7672f2326ee17e0fc80f4a6a6ac9d671b12

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

1. Zachary Teed
2. Jia Deng
3. Junda Cheng
4. Lahav Lipson
5. Xin Yang
6. Peng Guo
7. Gangwei Xu
8. Jia-Bin Huang

In Computer Vision and Pattern Recognition

1. Zachary Teed
2. Jia Deng
3. Lahav Lipson
4. Andrea Vedaldi
5. Dacheng Tao
6. Luc Van Gool
7. Gangwei Xu
8. Xiaogang Wang

Citations in the corpus

• Attention Concatenation Volume for Accurate and Efficient Stereo Matching (2022, methodology): “LEAStereo [3] has poor accuracy on Scene Flow; the performance of HITNet [18] in real-world scenarios (KITTI and ETH3D) is far inferior to our ACVNet.”
• RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching (2021, methodology): “In the forward pass, HITNet’s tile-based method must decide if each pixel lies on a plane.”