R-msfm: Recurrent multi-scale feature modulation for monocular depth estimating
Z Zhou, X Fan, P Shi, Y Xin - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
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 …
network architecture for self-supervised monocular depth estimation. R-MSFM extracts per …
Smurf: Self-teaching multi-frame unsupervised raft with full-image warping
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 …
of the art on all benchmarks by 36% to 40% and even outperforms several supervised …
Learning monocular depth in dynamic scenes via instance-aware projection consistency
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 …
multiple dynamic objects, ego-motion, and depth in a monocular camera setup without …
Skyeye: Self-supervised bird's-eye-view semantic mapping using monocular frontal view images
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 …
automated driving pipelines due to the rich representation they provide for decision-making …
Displacement-invariant matching cost learning for accurate optical flow estimation
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 …
deep stereo matching methods, in which 3D convolutions are applied on a 4D feature …
PVStereo: Pyramid voting module for end-to-end self-supervised stereo matching
Supervised learning with deep convolutional neural networks (DCNNs) has seen huge
adoption in stereo matching. However, the acquisition of large-scale datasets with well …
adoption in stereo matching. However, the acquisition of large-scale datasets with well …
LSVC: A learning-based stereo video compression framework
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 …
automotive stereo videos (ie, stereo videos from autonomous driving applications) from both …
Self-point-flow: Self-supervised scene flow estimation from point clouds with optimal transport and random walk
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 …
clouds has attracted increasing attention. In the self-supervised manner, establishing …
MDFlow: Unsupervised optical flow learning by reliable mutual knowledge distillation
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 …
unlabelled image pairs based on brightness constancy assumption and smoothness prior …
Adaptive cost volume representation for unsupervised high-resolution stereo matching
Learning-based stereomatching methods have produced remarkable results in recent years.
However, typical supervised learning-based methods always suffer from the non-negligible …
However, typical supervised learning-based methods always suffer from the non-negligible …