https://github.com/HeyingGithub/Baseline-project-for-MEGC2020_spotting
공식 코드Spotting Macro- and Micro-expression Intervals in Long Video Sequences
Papers with Code 아카이브
Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 133
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/HibaKob/MicroBundlePillarTrack
공식 코드https://github.com/Huangying-Zhan/DF-VO
공식 코드https://github.com/Huizerd/gym-quad
공식 코드Evolved Neuromorphic Control for High Speed Divergence-based Landings of MAVs
https://github.com/Hunter-Will/JDRL-mindspore
공식 코드Learning Single Image Defocus Deblurring with Misaligned Training Pairs
https://github.com/Hydragon516/PMN
공식 코드Unsupervised Video Object Segmentation via Prototype Memory Network
https://github.com/Jeckinchen/PhyCoBench
공식 코드https://github.com/JihyongOh/XVFI
공식 코드https://github.com/JingchunCheng/SegFlow
공식 코드SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
https://github.com/Jyxarthur/flowsam
공식 코드https://github.com/JzHuai0108/kalibr
공식 코드Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System
https://github.com/KUIS-AI-Tekalp-Research-Group/frame-prediction
공식 코드https://github.com/Kalana304/KORSAL
공식 코드KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
https://github.com/Kay1794/Motion-Graph-Video-Prediction
공식 코드Motion Graph Unleashed: A Novel Approach to Video Prediction
https://github.com/KevinDuarte/CapsuleVOS
공식 코드CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
https://github.com/Kwanss/PCLNet
공식 코드Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
https://github.com/LiUzHiAn/hf2vad
공식 코드https://github.com/LongguangWang/SOF-VSR
공식 코드Deep Video Super-Resolution using HR Optical Flow Estimation
https://github.com/LongguangWang/SOF-VSR-Super-Resolving-Optical-Flow-for-Video-Super-Resolution-
공식 코드Learning for Video Super-Resolution through HR Optical Flow Estimation
https://github.com/M-Elfeki/ThirdToFirst
공식 코드From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
https://github.com/MARSLab-UMN/DeepMultiviewDepth
공식 코드https://github.com/MCG-NKU/E2FGVI
공식 코드Towards An End-to-End Framework for Flow-Guided Video Inpainting
https://github.com/MKashifAli/Motion_Blind_Video_Stabilization
공식 코드https://github.com/MaureenZOU/TSAM
공식 코드Progressive Temporal Feature Alignment Network for Video Inpainting
https://github.com/MaxReimann/video-stream-consistency
공식 코드Interactive Control over Temporal Consistency while Stylizing Video Streams
https://github.com/Media-Smart/vedatad
공식 코드https://github.com/MungoMeng/Panorama-OpticalFlow
공식 코드High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow
https://github.com/NUST-Machine-Intelligence-Laboratory/HFAN
공식 코드Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
https://github.com/NVIDIA/semantic-segmentation
공식 코드SDCNet: Video Prediction Using Spatially-Displaced Convolution
https://github.com/NVlabs/PWC-Net
공식 코드PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
https://github.com/NVlabs/SENSE
공식 코드https://github.com/NVlabs/learningrigidity
공식 코드Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
https://github.com/OceanSummerDay/HSTA_MER
공식 코드Hierarchical Space-Time Attention for Micro-Expression Recognition
https://github.com/Prinsphield/LCV
공식 코드https://github.com/PruneTruong/DenseMatching
공식 코드Learning Accurate Dense Correspondences and When to Trust Them
https://github.com/PruneTruong/PDCNet
공식 코드Learning Accurate Dense Correspondences and When to Trust Them
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.