Papers with Code 아카이브
Point Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 15
Point Tracking, often referred to as Tracking any Point (TAP) involves acquiring, focusing on, and continuously tracking specific target point/points across video frames. The system identifies the target point, maintains focus, and predicts its movement, enabling smooth tracking even if the target moves unpredictably, or through occlusions. TAP has wide applications like object tracking, surveillance, and autonomous navigation.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/UZ-SLAMLab/SD-DefSLAM
공식 코드SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes
https://github.com/XingangPan/DragGAN
공식 코드Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
https://github.com/aliciachenw/PIPsUS
공식 코드https://github.com/amir-abdi/artisynth_point2point
공식 코드Muscle Excitation Estimation in Biomechanical Simulation Using NAF Reinforcement Learning
https://github.com/artemcher/myotracker
공식 코드Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
https://github.com/athaddius/stirmetrics
공식 코드Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
https://github.com/ayshrv/gmrw
공식 코드Self-Supervised Any-Point Tracking by Contrastive Random Walks
https://github.com/cardio-ai/mvhota
공식 코드https://github.com/coltonstearns/dynamic-gaussian-marbles
공식 코드Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos
https://github.com/cvlab-kaist/Chrono
공식 코드https://github.com/cvlab-kaist/locotrack
공식 코드https://github.com/cvlab-kaist/seurat
공식 코드https://github.com/dcharatan/flowmap
공식 코드FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent
https://github.com/deepmind/perception_test
공식 코드Perception Test: A Diagnostic Benchmark for Multimodal Video Models
https://github.com/deepmind/tapnet
공식 코드https://github.com/dinghaoxuan/oneshotlp
공식 코드A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
https://github.com/dqiaole/spot
공식 코드https://github.com/facebookresearch/co-tracker
공식 코드https://github.com/facebookresearch/vggt
공식 코드https://github.com/fedezocco/matvisiongluinh-pytorch_tensorflow
공식 코드Visual Material Characteristics Learning for Circular Healthcare
https://github.com/google-deepmind/tapnet
공식 코드https://github.com/gorkaydemir/track_on
공식 코드Track-On: Transformer-based Online Point Tracking with Memory
https://github.com/henry123-boy/SpaTrackerV2
공식 코드https://github.com/hiteshsaainew/optipixel_video_encode
공식 코드https://github.com/ifnspaml/s-amodal
공식 코드Foundation Models for Amodal Video Instance Segmentation in Automated Driving
https://github.com/jasonkks/pttr
공식 코드PTTR: Relational 3D Point Cloud Object Tracking with Transformer
https://github.com/ljh0v0/fmd-frechet-motion-distance
공식 코드Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
https://github.com/lpengyang/freedrag
공식 코드FreeDrag: Feature Dragging for Reliable Point-based Image Editing
https://github.com/martin-danelljan/Continuous-ConvOp
공식 코드Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
https://github.com/muhi-zatar/online_gradient_descent_fppt
공식 코드https://github.com/murray-wang/characonsist
공식 코드https://github.com/qianduoduolr/decomotion
공식 코드https://github.com/quickhdsdc/Point-Tracking-for-Displacement-Measurement-in-Railway-Applications
공식 코드https://github.com/rehglab/tracking_objectness
공식 코드https://github.com/riponazad/echotracker
공식 코드EchoTracker: Advancing Myocardial Point Tracking in Echocardiography
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.