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/PaddlePaddle/PaddleSeg
https://github.com/Pea-Shooter/ADNet
Attention-guided Network for Ghost-free High Dynamic Range Imaging
https://github.com/PruneTruong/GLU-Net
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
https://github.com/PruneTruong/GOCor
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
https://github.com/STVIR/seg2vid
https://github.com/SaipingZhang/DVC_P
https://github.com/SamvitJ/Accel
Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
https://github.com/Sense-X/X-Temporal
https://github.com/SforAiDl/vformer
Perceiver IO: A General Architecture for Structured Inputs & Outputs
https://github.com/Shualite/SFNet.pytorch
https://github.com/SuryaKalia/AaltoVision
DeMoN: Depth and Motion Network for Learning Monocular Stereo
https://github.com/T-a-g-z/Yotube-VOS-OVS
https://github.com/TRI-ML/vidar
Depth Field Networks for Generalizable Multi-view Scene Representation
https://github.com/Tangshitao/ClipShots
https://github.com/Tencent/ActionDetection-DBG
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
https://github.com/TimoStoff/events_contrast_maximization
Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion
https://github.com/ToyotaResearchInstitute/att-aware
https://github.com/Visual-Behavior/aloception
https://github.com/XiSHEN0220/RANSAC-Flow
https://github.com/XinyuSun/M3Video
Masked Motion Encoding for Self-Supervised Video Representation Learning
https://github.com/YapengTian/TDAN-VSR-CVPR-2020
TDAN: Temporally Deformable Alignment Network for Video Super-Resolution
https://github.com/YapengTian/TDAN_VSR
TDAN: Temporally Deformable Alignment Network for Video Super-Resolution
https://github.com/YashNita/Separate-Object-Sounds-by-Watching-Unlabeled-Video-PyTorch-
Im2Flow: Motion Hallucination from Static Images for Action Recognition
https://github.com/YiWeiHuang-stack/Squirrel-RIFE
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
https://github.com/Yijunmaverick/FlowGrounded-VideoPrediction
https://github.com/ZhenboSong/mono_velocity
https://github.com/a-doering/tracker_w_correlation_motion_model
https://github.com/a-imamshah/savi-pytorch
https://github.com/achalddave/segment-any-moving
https://github.com/adamtwig/segpred
https://github.com/afourast/avobjects
https://github.com/ahasan-haque/TMO-RAFT
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
https://github.com/aimerykong/predictive-filter-flow
Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
https://github.com/aj9011/Car-Speed-Prediction
Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
https://github.com/akashdhruv/jobrunner
BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.