https://github.com/mfaisal59/EpONet
공식 코드EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
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/mickeykang16/temporaleventstereo
공식 코드Temporal Event Stereo via Joint Learning with Stereoscopic Flow
https://github.com/microsoft/AirSim-NeurIPS2019-Drone-Racing
공식 코드https://github.com/microsoft/MaskFlownet
공식 코드MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
https://github.com/microsoft/dcvc
공식 코드https://github.com/microsoft/transductive-vos.pytorch
공식 코드https://github.com/micts/acgcn
공식 코드https://github.com/mingyushengsmy/amncutter
공식 코드https://github.com/mkashifali/metavideostab
공식 코드Harnessing Meta-Learning for Improving Full-Frame Video Stabilization
https://github.com/mlzxy/flowdino
공식 코드Optical Flow boosts Unsupervised Localization and Segmentation
https://github.com/monjurulkarim/rol_dataset
공식 코드https://github.com/moothes/a2s-v2
공식 코드Texture-guided Saliency Distilling for Unsupervised Salient Object Detection
https://github.com/msbrpp/MSBR
공식 코드https://github.com/msu-video-group/memfof
공식 코드MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
https://github.com/mtangemann/motion_energy_segmentation
공식 코드https://github.com/mulns/accflow
공식 코드https://github.com/multimediafor/aigvdet
공식 코드AI-Generated Video Detection via Spatio-Temporal Anomaly Learning
https://github.com/n3slami/Ef-RAFT
공식 코드https://github.com/naver/croco
공식 코드CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
https://github.com/nawidsayed/Cross-and-Learn
공식 코드https://github.com/nbei/Deep-Flow-Guided-Video-Inpainting
공식 코드https://github.com/ncherel/infusion
공식 코드Infusion: internal diffusion for inpainting of dynamic textures and complex motion
https://github.com/neu-vi/ezflow
공식 코드https://github.com/neufieldrobotics/neuflow
공식 코드NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices
https://github.com/neufieldrobotics/neuflow_v2
공식 코드NeuFlow v2: High-Efficiency Optical Flow Estimation on Edge Devices
https://github.com/neuroailab/eisen
공식 코드Unsupervised Segmentation in Real-World Images via Spelke Object Inference
https://github.com/neuromorphic-paris/frog
공식 코드A Framework for Event-based Computer Vision on a Mobile Device
https://github.com/nevsnev/fgdvi
공식 코드https://github.com/nie-lang/Multi-Grid-Deep-Homography
공식 코드Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
https://github.com/nie-lang/rotationcorrection
공식 코드https://github.com/nie-lang/stabstitch
공식 코드Eliminating Warping Shakes for Unsupervised Online Video Stitching
https://github.com/nie-lang/stabstitch2
공식 코드StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps
https://github.com/nihaomiao/cvpr23_lfdm
공식 코드Conditional Image-to-Video Generation with Latent Flow Diffusion Models
https://github.com/niika/SIDAR
공식 코드https://github.com/nikitinvv/tomoalign
공식 코드https://github.com/njuvision/eventtransformer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.