Hyperpixel Flow: Semantic Correspondence with Multi-Layer Neural Features
Abstract
Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.
Cite
Text
Min et al. "Hyperpixel Flow: Semantic Correspondence with Multi-Layer Neural Features." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00349Markdown
[Min et al. "Hyperpixel Flow: Semantic Correspondence with Multi-Layer Neural Features." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/min2019iccv-hyperpixel/) doi:10.1109/ICCV.2019.00349BibTeX
@inproceedings{min2019iccv-hyperpixel,
title = {{Hyperpixel Flow: Semantic Correspondence with Multi-Layer Neural Features}},
author = {Min, Juhong and Lee, Jongmin and Ponce, Jean and Cho, Minsu},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00349},
url = {https://mlanthology.org/iccv/2019/min2019iccv-hyperpixel/}
}