https://github.com/damien911224/theWorldInSafety
Two-Stream Convolutional Networks for Action Recognition in Videos
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/dbbert/dfn
https://github.com/deepmind/perception_test
https://github.com/derek-baker/group3
Spotting Macro- and Micro-expression Intervals in Long Video Sequences
https://github.com/deu439/MCMC-optical-flow
https://github.com/donghao51/multiood
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
https://github.com/drhdr-user/drhdr
Attention-guided Network for Ghost-free High Dynamic Range Imaging
https://github.com/dyelax/Adversarial_Video_Generation
https://github.com/ekgibbons/pytorch-sepconv
Video Frame Interpolation via Adaptive Separable Convolution
https://github.com/erezposner/Fast_Dense_Feature_Extraction
https://github.com/esakak/sevc
https://github.com/esceptico/perceiver-io
Perceiver IO: A General Architecture for Structured Inputs & Outputs
https://github.com/eynaij/X-Temporal_catdim
https://github.com/facebookresearch/SegmPred
https://github.com/facebookresearch/instpred
Predicting Future Instance Segmentation by Forecasting Convolutional Features
https://github.com/facebookresearch/supervision-by-registration
https://github.com/feihuzhang/separableflow
https://github.com/fperezgamonal/faldoi-ipol
FALDOI: A new minimization strategy for large displacement variational optical flow
https://github.com/fpsandnoob/pwc_net
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
https://github.com/fpthink/stnet
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
https://github.com/fpthink/v2b
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
https://github.com/fzi-forschungszentrum-informatik/mrf
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth
https://github.com/gengshan-y/VCN
https://github.com/google-deepmind/perception_test
https://github.com/google-research/google-research/tree/master/assemblenet
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
https://github.com/google-research/opticalflow-autoflow
https://github.com/google-research/sparf
Learning Accurate Dense Correspondences and When to Trust Them
https://github.com/googleinterns/deep-stabilization
https://github.com/goutamgmb/NTIRE21_BURSTSR
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
https://github.com/goutamgmb/deep-burst-sr
https://github.com/goutamgmb/deep-rep
https://github.com/guanfuchen/video_obj
https://github.com/guanyingc/DeepHDRVideo
HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset
https://github.com/gulvarol/ltc
https://github.com/guoxixu/TrafficFlowTracking
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
https://github.com/gurpreet-singh135/Image-Interpolation-via-adaptive-separable-convolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.