Soft Cross Entropy Loss and Bottleneck Tri-Cost Volume for Efficient Stereo Depth Prediction

Tyler Nuanes, Matt Elsey, Aswin Sankaranarayanan, John Shen. Soft Cross Entropy Loss and Bottleneck Tri-Cost Volume for Efficient Stereo Depth Prediction. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021, virtual, June 19-25, 2021. pages 2846-2854, Computer Vision Foundation / IEEE, 2021. [doi]

Abstract

Abstract is missing.