Traditional and modern strategies for optical flow: an investigation
STH Shah, X Xuezhi - SN Applied Sciences, 2021 - Springer
Abstract Optical Flow Estimation is an essential component for many image processing
techniques. This field of research in computer vision has seen an amazing development in …
techniques. This field of research in computer vision has seen an amazing development in …
Review of stereo matching algorithms based on deep learning
K Zhou, X Meng, B Cheng - Computational intelligence and …, 2020 - Wiley Online Library
Stereo vision is a flourishing field, attracting the attention of many researchers. Recently,
leveraging on the development of deep learning, stereo matching algorithms have achieved …
leveraging on the development of deep learning, stereo matching algorithms have achieved …
Self-supervised monocular depth estimation: Solving the dynamic object problem by semantic guidance
M Klingner, JA Termöhlen, J Mikolajczyk… - Computer Vision–ECCV …, 2020 - Springer
Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene
information from single camera images, which is trainable on arbitrary image sequences …
information from single camera images, which is trainable on arbitrary image sequences …
Simple unsupervised object-centric learning for complex and naturalistic videos
Unsupervised object-centric learning aims to represent the modular, compositional, and
causal structure of a scene as a set of object representations and thereby promises to …
causal structure of a scene as a set of object representations and thereby promises to …
Digging into self-supervised monocular depth estimation
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this
limitation, self-supervised learning has emerged as a promising alternative for training …
limitation, self-supervised learning has emerged as a promising alternative for training …
Geonet: Unsupervised learning of dense depth, optical flow and camera pose
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 …
flow and ego-motion estimation from videos. The three components are coupled by the …
Bmbc: Bilateral motion estimation with bilateral cost volume for video interpolation
Video interpolation increases the temporal resolution of a video sequence by synthesizing
intermediate frames between two consecutive frames. We propose a novel deep-learning …
intermediate frames between two consecutive frames. We propose a novel deep-learning …
Perceiving spectral variation: Unsupervised spectrum motion feature learning for hyperspectral image classification
Y Sun, B Liu, X Yu, A Yu, K Gao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In recent years, deep-learning-based hyperspectral image (HSI) classification methods have
achieved significant development. The superior capability of feature extraction from these …
achieved significant development. The superior capability of feature extraction from these …
Df-net: Unsupervised joint learning of depth and flow using cross-task consistency
We present an unsupervised learning framework for simultaneously training single-view
depth prediction and optical flow estimation models using unlabeled video sequences …
depth prediction and optical flow estimation models using unlabeled video sequences …
Selflow: Self-supervised learning of optical flow
We present a self-supervised learning approach for optical flow. Our method distills reliable
flow estimations from non-occluded pixels, and uses these predictions as ground truth to …
flow estimations from non-occluded pixels, and uses these predictions as ground truth to …