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/nihui/rife-ncnn-vulkan
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
https://github.com/nikankind/Reproduce-Article-Representation-Flow-for-Action-Recognition-with-PaddlePaddle
https://github.com/ning22/Motion-Compensated-Dynamic-MRI-Reconstruction-with-Local-Affine-Optical-Flow-Estimation
Motion Compensated Dynamic MRI Reconstruction with Local Affine Optical Flow Estimation
https://github.com/nv-nguyen/pizza
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
https://github.com/nvlabs/emernerf
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
https://github.com/obvious-research/OnlyFlow
OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models
https://github.com/open-mmlab/mmaction2
https://github.com/open-mmlab/mmflow
https://github.com/open-mmlab/mmpose
Learning Temporal Pose Estimation from Sparsely-Labeled Videos
https://github.com/osmr/propainter
ProPainter: Improving Propagation and Transformer for Video Inpainting
https://github.com/osmr/pytorchcv
https://github.com/owl-project/ViSII
NViSII: A Scriptable Tool for Photorealistic Image Generation
https://github.com/parthapratimbanik/facial-keypoint-detection-udacity-ppb
https://github.com/philferriere/tfoptflow
https://github.com/pilot7747/sldl
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
https://github.com/plusgood-steven/id-blau
https://github.com/ppliuboy/DDFlow
DDFlow: Learning Optical Flow with Unlabeled Data Distillation
https://github.com/princeton-vl/Princeton365
https://github.com/princeton-vl/d3dhelper
https://github.com/prophesee-ai/prophesee-automotive-dataset-toolbox
https://github.com/pytorch/vision
https://github.com/qianyuzqy/TransVOD_plusplus
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers
https://github.com/qingsenyangit/AHDRNet
Attention-guided Network for Ghost-free High Dynamic Range Imaging
https://github.com/raghudeep/netwarp_public
https://github.com/raunaks13/GeoNet-PyTorch
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
https://github.com/raunaks13/carla-SIGNet
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
https://github.com/ravikt/sceneflowgan
https://github.com/raymondwang987/nvds
https://github.com/remibasaru/Flow-Net
https://github.com/rhgao/Deep-MIML-Network
Im2Flow: Motion Hallucination from Static Images for Action Recognition
https://github.com/rhgao/Im2Flow
Im2Flow: Motion Hallucination from Static Images for Action Recognition
https://github.com/rhgao/separating-object-sounds
Im2Flow: Motion Hallucination from Static Images for Action Recognition
https://github.com/rickyHong/tfoptflow-repl
https://github.com/rmalav15/Super-SloMo
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
https://github.com/rogerhcheng/LiteFlowNet2-TF2
A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.