In this paper, we propose Recurrent Multi-Scale Feature Modulation (R-MSFM), a new deep
network architecture for self-supervised monocular depth estimation. R-MSFM extracts per …

We present SMURF, a method for unsupervised learning of optical flow that improves state
of the art on all benchmarks by 36% to 40% and even outperforms several supervised …

We present an end-to-end joint training framework that explicitly models 6-DoF motion of
multiple dynamic objects, ego-motion, and depth in a monocular camera setup without …

Abstract Bird's-Eye-View (BEV) semantic maps have become an essential component of
automated driving pipelines due to the rich representation they provide for decision-making …

Learning matching costs has been shown to be critical to the success of the state-of-the-art
deep stereo matching methods, in which 3D convolutions are applied on a 4D feature …

Supervised learning with deep convolutional neural networks (DCNNs) has seen huge
adoption in stereo matching. However, the acquisition of large-scale datasets with well …

In this work, we propose the first end-to-end optimized framework for compressing
automotive stereo videos (ie, stereo videos from autonomous driving applications) from both …

Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point
clouds has attracted increasing attention. In the self-supervised manner, establishing …

Recent works have shown that optical flow can be learned by deep networks from
unlabelled image pairs based on brightness constancy assumption and smoothness prior …

Learning-based stereomatching methods have produced remarkable results in recent years.
However, typical supervised learning-based methods always suffer from the non-negligible …