https://github.com/junbongjang/contour-tracking
공식 코드Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses
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/junpan19/ETDM
공식 코드Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
https://github.com/junting/seg2vid
공식 코드https://github.com/jytime/DICL-Flow
공식 코드Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
https://github.com/jytime/Deep-SfM-Revisited
공식 코드https://github.com/k4ntz/moc
공식 코드Boosting Object Representation Learning via Motion and Object Continuity
https://github.com/kamanphoebe/motiondetection
공식 코드https://github.com/kamruleee51/ddc-ac-dlir
공식 코드https://github.com/kerenfu/rdvs
공식 코드https://github.com/kevin-ssy/Optical-Flow-Guided-Feature
공식 코드Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
https://github.com/kevinhuangxf/fingerveinrecognition
공식 코드Motion Transfer-Driven intra-class data augmentation for Finger Vein Recognition
https://github.com/kiyoon/channel_sampling
공식 코드Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
https://github.com/knmac/LCDC_release
공식 코드https://github.com/kuai-lab/soundini-official
공식 코드https://github.com/kuis-ai-tekalp-research-group/perceptual-vsr
공식 코드Spatio-Temporal Perception-Distortion Trade-off in Learned Video SR
https://github.com/la30/agflow
공식 코드https://github.com/la30/gaflow
공식 코드https://github.com/lab-midas/lapnet
공식 코드LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging
https://github.com/lab-notebooks/outflow-forcing-bubbleml
공식 코드BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
https://github.com/leiwangr/video-ar
공식 코드https://github.com/lelimite4444/BridgeDepthFlow
공식 코드Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
https://github.com/lhoangan/341n143
공식 코드Three for one and one for three: Flow, Segmentation, and Surface Normals
https://github.com/lhoangan/arap_flow
공식 코드https://github.com/li-jicheng/mmasd-a-multimodal-dataset-for-autism-intervention-analysis
공식 코드MMASD: A Multimodal Dataset for Autism Intervention Analysis
https://github.com/lili0415/dpu-ood-detection
공식 코드DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
https://github.com/linjing7/VR-Baseline
공식 코드https://github.com/linyicheng1/LET-NET
공식 코드Breaking of brightness consistency in optical flow with a lightweight CNN network
https://github.com/lisiyao21/animerun
공식 코드AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
https://github.com/littlespray/SKFlow
공식 코드https://github.com/littlespray/streamflow
공식 코드StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
https://github.com/liuqi-creat/sigformer
공식 코드SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation
https://github.com/liuzhen03/nndvs
공식 코드https://github.com/liuziyang123/faminet
공식 코드https://github.com/lixiaowen-xw/diffueraser
공식 코드https://github.com/liyinibristol/Zero-TIG
공식 코드Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
https://github.com/liyucs/jdrl
공식 코드Learning Single Image Defocus Deblurring with Misaligned Training Pairs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.