Computer vision for autonomous vehicles: Problems, datasets and state of the art

J Janai, F Güney, A Behl, A Geiger - Foundations and Trends® …, 2020 - nowpublishers.com
Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

A review on deep learning techniques for video prediction

S Oprea, P Martinez-Gonzalez… - … on Pattern Analysis …, 2020 - ieeexplore.ieee.org
The ability to predict, anticipate and reason about future outcomes is a key component of
intelligent decision-making systems. In light of the success of deep learning in computer …

Gmflow: Learning optical flow via global matching

H Xu, J Zhang, J Cai… - Proceedings of the …, 2022 - openaccess.thecvf.com
Learning-based optical flow estimation has been dominated with the pipeline of cost volume
with convolutions for flow regression, which is inherently limited to local correlations and …

Unifying flow, stereo and depth estimation

H Xu, J Zhang, J Cai, H Rezatofighi… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …

Grounding image matching in 3d with mast3r

V Leroy, Y Cabon, J Revaud - European Conference on Computer Vision, 2024 - Springer
Image Matching is a core component of all best-performing algorithms and pipelines in 3D
vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to …

Learning to estimate hidden motions with global motion aggregation

S Jiang, D Campbell, Y Lu, H Li… - Proceedings of the …, 2021 - openaccess.thecvf.com
Occlusions pose a significant challenge to optical flow algorithms that rely on local
evidences. We consider an occluded point to be one that is imaged in the first frame but not …

R2d2: Reliable and repeatable detector and descriptor

J Revaud, C De Souza… - Advances in neural …, 2019 - proceedings.neurips.cc
Interest point detection and local feature description are fundamental steps in many
computer vision applications. Classical approaches are based on a detect-then-describe …

Depth-aware video frame interpolation

W Bao, WS Lai, C Ma, X Zhang… - Proceedings of the …, 2019 - openaccess.thecvf.com
Video frame interpolation aims to synthesize nonexistent frames in-between the original
frames. While significant advances have been made from the recent deep convolutional …

Learning correspondence from the cycle-consistency of time

X Wang, A Jabri, AA Efros - … of the IEEE/CVF conference on …, 2019 - openaccess.thecvf.com
We introduce a self-supervised method for learning visual correspondence from unlabeled
video. The main idea is to use cycle-consistency in time as free supervisory signal for …

Geonet: Unsupervised learning of dense depth, optical flow and camera pose

Z Yin, J Shi - Proceedings of the IEEE conference on …, 2018 - openaccess.thecvf.com
We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical
flow and ego-motion estimation from videos. The three components are coupled by the …