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/RViMLab/oflibnumpy
공식 코드Oflib: Facilitating Operations with and on Optical Flow Fields in Python
https://github.com/RViMLab/oflibpytorch
공식 코드Oflib: Facilitating Operations with and on Optical Flow Fields in Python
https://github.com/Randle-Github/AGGN
공식 코드Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network
https://github.com/RuijieZhu94/MotionGS
공식 코드MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
https://github.com/SJTU-LuHe/TransVOD
공식 코드End-to-End Video Object Detection with Spatial-Temporal Transformers
https://github.com/SSAW14/STD2P
공식 코드STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
https://github.com/SeokjuLee/Insta-DM
공식 코드Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
https://github.com/TJUMMG/DS-Net
공식 코드DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection
https://github.com/Tencent/DepthCrafter
공식 코드DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
https://github.com/TencentARC/VideoPainter
공식 코드VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
https://github.com/TengdaHan/CoCLR
공식 코드Self-supervised Co-training for Video Representation Learning
https://github.com/TengdaHan/MemDPC
공식 코드Memory-augmented Dense Predictive Coding for Video Representation Learning
https://github.com/Tengfei-Wang/Implicit-Internal-Video-Inpainting
공식 코드Internal Video Inpainting by Implicit Long-range Propagation
https://github.com/TonyHongtaoWu/RainMamba
공식 코드RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining
https://github.com/TonyLianLong/RCF-UnsupVideoSeg
공식 코드Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
https://github.com/TuSimple/LiDAR_SOT
공식 코드Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
https://github.com/UZ-SLAMLab/DrunkardsOdometry
공식 코드The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes
https://github.com/VLOGroup/bp-layers
공식 코드Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
https://github.com/VLOGroup/dvs-reconstruction
공식 코드Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation
https://github.com/VincentBouget/rain-nowcasting-with-fusion-of-rainfall-and-wind-data-article
공식 코드Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting
https://github.com/WISION-Lab/event-nn-pytorch
공식 코드https://github.com/WISION-Lab/event-nn-tf
공식 코드https://github.com/WendyShang/dqn_zoo
공식 코드https://github.com/WendyShang/flare
공식 코드https://github.com/Xianhang/EDSC-pytorch
공식 코드Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution
https://github.com/XiaoyuShi97/FlowFormerPlusPlus
공식 코드FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
https://github.com/XiaoyuShi97/VideoFlow
공식 코드VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
https://github.com/YBQian-Roy/UCF-Crime-DVS
공식 코드UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks
https://github.com/YanchaoYang/Conditional-Prior-Networks
공식 코드https://github.com/YongyiTang92/MoNet-Features
공식 코드Hallucinating Optical Flow Features for Video Classification
https://github.com/YuhaoCheng/OpticalFlow_Kinetic
공식 코드Rethink Predicting the Optical Flow with the Kinetics Perspective
https://github.com/Yui010206/CREMA
공식 코드CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
https://github.com/Yui010206/MoPRL
공식 코드Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
https://github.com/abdo-eldesokey/RAFT-NCUP
공식 코드Normalized Convolution Upsampling for Refined Optical Flow Estimation
https://github.com/acceleration-magnification/sources
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.