Addressing the Scale Shrinkage Problem in Learning-based Binocular Depth Estimation
Gang Guo,Yixu Song,Fuchun Sun,Gang Guo,Yixu Song,Fuchun Sun
Binocular depth estimation is a fundamental problem in computer vision. Learning-based models have achieved significant performance improvements on public datasets in recent years. Our study finds that the performance of the current state-of-the-art deep learning-based models deteriorates significantly in distant areas. We point out that these deep learning-based models suffer from a scale shrinka...
