LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation

By Sunok Kim, Seungryong Kim, Dongbo Min, K. Sohn. 2019

61 citations recorded by the source corpus.

We present a novel method that estimates confidence map of an initial disparity by making full use of tri-modal input, including matching cost, disparity, and color image through deep networks. The proposed network, termed as Locally Adaptive Fusion Networks (LAF-Net), learns locally-varying attention and scale maps to fuse the tri-modal confidence features. The attention inference networks encode the importance of tri-modal confidence features and then concatenate them using the attention maps in an adaptive and dynamic fashion. This enables us to make an optimal fusion of the heterogeneous features, compared to a simple concatenation technique that is commonly used in conventional approaches. In addition, to encode the confidence features with locally-varying receptive fields, the scale inference networks learn the scale map and warp the fused confidence features through convolutional spatial transformer networks. Finally, the confidence map is progressively estimated in the recursive refinement networks to enforce a spatial context and local consistency. Experimental results show that this model outperforms the state-of-the-art methods on various benchmarks.

Subfields: Computer Vision and Pattern Recognition, Media Technology, 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

1. Shiji Song
2. Yulin Wang
3. Gao Huang
4. Yizeng Han
5. Le Yang
6. Honghui Wang
7. Stefano Mattoccia
8. Fabio Tosi

In Media Technology

1. Stefano Mattoccia
2. Fabio Tosi
3. Gao Huang
4. Shiji Song
5. Matteo Poggi
6. Yulin Wang
7. Filippo Aleotti

In 3D Vision & Pose

1. Stefano Mattoccia

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “Others Document classification [146], Link prediction [221], Graph classification [113], Stereo confidence estimation [222], Recommendation systems [223]”
• On the Uncertainty of Self-Supervised Monocular Depth Estimation (2020, background): “, the cost volume [24], then by means of deep learning on already estimated disparity maps [55, 61, 54, 67, 31].”