Video super-resolution based on deep learning: a comprehensive survey

H Liu, Z Ruan, P Zhao, C Dong, F Shang, Y Liu… - Artificial Intelligence …, 2022 - Springer
Video super-resolution (VSR) is reconstructing high-resolution videos from low resolution
ones. Recently, the VSR methods based on deep neural networks have made great …

[HTML][HTML] An overview to visual odometry and visual SLAM: Applications to mobile robotics

K Yousif, A Bab-Hadiashar… - Intelligent Industrial …, 2015 - Springer
This paper is intended to pave the way for new researchers in the field of robotics and
autonomous systems, particularly those who are interested in robot localization and …

[PDF][PDF] 目标跟踪算法综述

孟琭, 杨旭 - 自动化学报, 2019 - aas.net.cn
摘要目标跟踪一直以来都是计算机视觉领域的关键问题, 最近随着人工智能技术的飞速发展,
运动目标跟踪问题得到了越来越多的关注. 本文对主流目标跟踪算法进行了综述, 首先 …

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 …

Tdan: Temporally-deformable alignment network for video super-resolution

Y Tian, Y Zhang, Y Fu, C Xu - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
Video super-resolution (VSR) aims to restore a photo-realistic high-resolution (HR) video
frame from both its corresponding low-resolution (LR) frame (reference frame) and multiple …

Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume

D Sun, X Yang, MY Liu, J Kautz - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net
has been designed according to simple and well-established principles: pyramidal …

The surprising effectiveness of diffusion models for optical flow and monocular depth estimation

S Saxena, C Herrmann, J Hur, A Kar… - Advances in …, 2024 - proceedings.neurips.cc
Denoising diffusion probabilistic models have transformed image generation with their
impressive fidelity and diversity. We show that they also excel in estimating optical flow and …

Global matching with overlapping attention for optical flow estimation

S Zhao, L Zhao, Z Zhang, E Zhou… - Proceedings of the …, 2022 - openaccess.thecvf.com
Optical flow estimation is a fundamental task in computer vision. Recent direct-regression
methods using deep neural networks achieve remarkable performance improvement …

Super slomo: High quality estimation of multiple intermediate frames for video interpolation

H Jiang, D Sun, V Jampani, MH Yang… - Proceedings of the …, 2018 - openaccess.thecvf.com
Given two consecutive frames, video interpolation aims at generating intermediate frame (s)
to form both spatially and temporally coherent video sequences. While most existing …

Video frame interpolation via adaptive separable convolution

S Niklaus, L Mai, F Liu - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Standard video frame interpolation methods first estimate optical flow between input frames
and then synthesize an intermediate frame guided by motion. Recent approaches merge …