Do End-to-end Stereo Algorithms Under-utilize Information?

14 Oct 2020 Changjiang Cai Philippos Mordohai

Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive convolutions and down-sampling and up-sampling operations, these cost aggregation mechanisms do not take full advantage of the information available in the images... (read more)

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
1x1 Convolution
Convolutions
Residual Connection
Skip Connections
ReLU
Activation Functions
Softmax
Output Functions
Layer Normalization
Normalization
Convolution
Convolutions
Global Context Block
Image Model Blocks
GCNet
Object Detection Models