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/acnext/scsim
공식 코드https://github.com/adnortje/deepvideo
공식 코드Deep motion estimation for parallel inter-frame prediction in video compression
https://github.com/aeitel/self_deepmask
공식 코드Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction
https://github.com/afruehstueck/VIVE3D
공식 코드VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs
https://github.com/aharley/pips
공식 코드Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
https://github.com/aharley/segaware
공식 코드Segmentation-Aware Convolutional Networks Using Local Attention Masks
https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds
공식 코드https://github.com/ahmedhumais/e-stmflow
공식 코드Spatio-Temporal State Space Model For Efficient Event-Based Optical Flow
https://github.com/ahmetakman/e-vfia
공식 코드E-VFIA : Event-Based Video Frame Interpolation with Attention
https://github.com/aim-uofa/rgm
공식 코드https://github.com/aimi-lab/robust-pose-estimator
공식 코드Learning How To Robustly Estimate Camera Pose in Endoscopic Videos
https://github.com/ais-bonn/temporal_latticenet
공식 코드Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice
https://github.com/alex04072000/FuSta
공식 코드https://github.com/alex04072000/ObstructionRemoval
공식 코드https://github.com/alex04072000/SOLD
공식 코드Learning to See Through Obstructions with Layered Decomposition
https://github.com/alexzzhu/EventGAN
공식 코드EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
https://github.com/algolzw/bsrt
공식 코드BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
https://github.com/aliciachenw/PIPsUS
공식 코드https://github.com/amatov/datasettracker
공식 코드Real-Time Image Analysis Software Suitable for Resource-Constrained Computing
https://github.com/amontib/gpu-prnu-sift
공식 코드GPU-accelerated SIFT-aided source identification of stabilized videos
https://github.com/angus-apps/AEMOT
공식 코드https://github.com/annbless/ovs_stabilization
공식 코드Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
https://github.com/anonrep/iba-for-video-sequences
공식 코드Extending Information Bottleneck Attribution to Video Sequences
https://github.com/anonymous-p/Flickering_Adversarial_Video
공식 코드Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
https://github.com/anoymized/multi-order-motion-model
공식 코드Machine Learning Modeling for Multi-order Human Visual Motion Processing
https://github.com/anshulbshah/PoseAction
공식 코드https://github.com/anshulbshah/steps
공식 코드STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos
https://github.com/anuragranj/cc
공식 코드https://github.com/anuragranj/humanflow
공식 코드https://github.com/anuragranj/spynet
공식 코드https://github.com/arnabkmondal/RespVAD
공식 코드RespVAD: Voice Activity Detection via Video-Extracted Respiration Patterns
https://github.com/askerlee/craft
공식 코드CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
https://github.com/auto-pilot/obstacle-avoidance
공식 코드Autonomous Driving Implementation in an Experimental Environment
https://github.com/autonomousvision/unimatch
공식 코드https://github.com/avinashpaliwal/Deep-SloMo
공식 코드Deep Slow Motion Video Reconstruction with Hybrid Imaging System
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.