The Sampling-Gaussian for Stereo Matching

The soft-argmax operation is widely adopted in neural network-based stereo matching methods to enable differentiable regression of disparity. However, networks trained with soft-argmax tend to predict multimodal probability distributions due to the absence of explicit constraints on the shape of the distribution. Previous methods leveraged Laplacian distributions and cross-entropy for training but failed to effectively improve accuracy and even increased the network’s processing time. In this paper, we propose a novel method called Sampling-Gaussian as a substitute for soft-argmax. It improves accuracy without increasing inference time. We innovatively interpret the training process as minimizing the distance in vector space and propose a combined loss of L1 loss and cosine similarity loss. We leveraged the normalized discrete Gaussian distribution for supervision. Moreover, we identified two issues in previous methods and proposed extending the disparity range and employing bilinear interpolation as solutions. We have conducted comprehensive experiments to demonstrate the superior performance of our Sampling-Gaussian method. The experimental results prove that we have achieved better accuracy on five baseline methods across four datasets. Moreover, we have achieved significant improvements on small datasets and models with weaker generalization capabilities. Our method is easy to implement, and the code is available online.

Authors

• Baiyu Pan
• Bowen Yao
• Jichao Jiao
• Jianxin Pang
• Jun Cheng

Keywords

• Training
• Interpolation
• Accuracy
• Laplace equations
• Codes
• Shape
• Gaussian distribution
• Vectors
• Probability distribution
• Intelligent robots
• Stereo Matching
• Bimodal
• Small Datasets
• Shape Of Distribution
• Baseline Methods
• Bilinear Interpolation
• L1 Loss
• Laplace Distribution
• Disparity Range
• Softmax
• Generalization Ability
• Cross-entropy Loss
• Dot Product
• Trilinear Interpolation
• Endpoint Error
• Distribution-based Methods
• Cost Volume