Papers with Code 아카이브

Optical Flow Estimation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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://bitbucket.org/Cross_Product/optical_flow

공식 코드

A torus model for optical flow

https://github.com/11maxed11/phase-based-action-recognition

공식 코드

Using phase instead of optical flow for action recognition

https://github.com/16lemoing/ccvs

공식 코드

CCVS: Context-aware Controllable Video Synthesis

https://github.com/16lemoing/dot

공식 코드

Dense Optical Tracking: Connecting the Dots

https://github.com/3dperceptionlab/hierarchicalactionrecognition

공식 코드

Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context

https://github.com/3huo/MVDI

공식 코드

Action Recognition for Depth Video using Multi-view Dynamic Images

https://github.com/A-Kerim/SyntheticData4VideoStabilization

공식 코드

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions

https://github.com/AaltoVision/camera-gyro-calibration

공식 코드

Robust Gyroscope-Aided Camera Self-Calibration

https://github.com/AlanZhang1995/TwoStreamSR

공식 코드

Two-Stream Action Recognition-Oriented Video Super-Resolution

https://github.com/AlexanderParkin/CASIA-SURF_CeFA

공식 코드

Creating Artificial Modalities to Solve RGB Liveness

https://github.com/Annbless/DUTCode

공식 코드

DUT: Learning Video Stabilization by Simply Watching Unstable Videos

https://github.com/ArashNasrEsfahani/Object-Rearrangement-in-Dynamic-Environments

공식 코드

AI-Driven Relocation Tracking in Dynamic Kitchen Environments

https://github.com/AtlantixJJ/frame-difference-loss

공식 코드

Frame Difference-Based Temporal Loss for Video Stylization

https://github.com/B1ueber2y/TrianFlow

공식 코드

Towards Better Generalization: Joint Depth-Pose Learning without PoseNet

https://github.com/BillOuyang/OGSFNet

공식 코드

Occlusion Guided Scene Flow Estimation on 3D Point Clouds

https://github.com/Breakend/MotionDetection

공식 코드

An Analysis of Parallelized Motion Masking Using Dual-Mode Single Gaussian Models

https://github.com/CIRS-Girona/ecarla-scenes

공식 코드

eCARLA-scenes: A synthetically generated dataset for event-based optical flow prediction

https://github.com/CIRS-Girona/ewiz

공식 코드

eCARLA-scenes: A synthetically generated dataset for event-based optical flow prediction

https://github.com/CVLAB-Unibo/omeganet

공식 코드

Distilled Semantics for Comprehensive Scene Understanding from Videos

https://github.com/ChenyangLEI/deep-video-prior

공식 코드

Blind Video Temporal Consistency via Deep Video Prior

https://github.com/D-X-Y/landmark-detection

공식 코드

Supervision by Registration and Triangulation for Landmark Detection

https://github.com/DavHoffmann/Multi-humanDataGeneration

공식 코드

Learning Multi-Human Optical Flow

https://github.com/DediGadot/PatchBatch

공식 코드

Optical Flow Requires Multiple Strategies (but only one network)

https://github.com/DreamIP/StrainNet

공식 코드

When Deep Learning Meets Digital Image Correlation

https://github.com/EasonChen99/EVLoc

공식 코드

EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration

https://github.com/Etienne-Meunier-Inria/EM-Flow-Segmentation

공식 코드

EM-driven unsupervised learning for efficient motion segmentation

https://github.com/FilippoAleotti/Dwarf-Tensorflow

공식 코드

Learning End-To-End Scene Flow by Distilling Single Tasks Knowledge

https://github.com/GiannisPikoulis/FG2021-BoLD

공식 코드

Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild

https://github.com/GibranBenitez/IPN-hand

공식 코드

IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition

https://github.com/GuoLusjtu/DVC

공식 코드

DVC: An End-to-end Deep Video Compression Framework

https://github.com/HKUST-Aerial-Robotics/Flow-Motion-Depth

공식 코드

Flow-Motion and Depth Network for Monocular Stereo and Beyond

https://github.com/HYOJINPARK/TTVOS

공식 코드

TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss

https://github.com/HanLingsgjk/CSCV

공식 코드

ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video

https://github.com/HaojunYu1998/UltraDet

공식 코드

Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection

https://github.com/Haotianz94/IL_video_inpainting

공식 코드

An Internal Learning Approach to Video Inpainting

https://github.com/HarmoniaLeo/FRLW-EvD

공식 코드

Motion Robust High-Speed Light-Weighted Object Detection With Event Camera

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.