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://github.com/sniklaus/softmax-splatting

공식 코드

Softmax Splatting for Video Frame Interpolation

https://github.com/sollynoay/mmp-rnn

공식 코드

Efficient Video Deblurring Guided by Motion Magnitude

https://github.com/srcn-ivl/ebme

공식 코드

Enhanced Bi-directional Motion Estimation for Video Frame Interpolation

https://github.com/srcn-ivl/upr-net

공식 코드

A Unified Pyramid Recurrent Network for Video Frame Interpolation

https://github.com/steffenczolbe/topologicalchangedetection

공식 코드

Spot the Difference: Detection of Topological Changes via Geometric Alignment

https://github.com/stephenphillips42/erl_egomotion

공식 코드

Fast, Robust, Continuous Monocular Egomotion Computation

https://github.com/stevenliuwen/ano_pred_cvpr2018

공식 코드

Future Frame Prediction for Anomaly Detection -- A New Baseline

https://github.com/sthoduka/motion_anomaly_detection

공식 코드

Using Visual Anomaly Detection for Task Execution Monitoring

https://github.com/suhwan-cho/tmo

공식 코드

Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation

https://github.com/sylqiu/tof_rgbd_processing

공식 코드

Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module

https://github.com/syscv/maskfreevis

공식 코드

Mask-Free Video Instance Segmentation

https://github.com/tanvir-utexas/adave

공식 코드

Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior

https://github.com/tarun005/FLAVR

공식 코드

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

https://github.com/teaghan/flownet_pet

공식 코드

FlowNet-PET: Unsupervised Learning to Perform Respiratory Motion Correction in PET Imaging

https://github.com/tensorflow/models

공식 코드

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/assemblenet

공식 코드

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures

https://github.com/thomasweng15/FabricFlowNet

공식 코드

FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy

https://github.com/tianhongdai/wavelet-hdr

공식 코드

Wavelet-Based Network For High Dynamic Range Imaging

https://github.com/tobiasfshr/MOTSFusion

공식 코드

Track to Reconstruct and Reconstruct to Track

https://github.com/tofis/deepmocap

공식 코드

DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors

https://github.com/tommygong08/msif

공식 코드

Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach

https://github.com/tonniia/zero2hero

공식 코드

Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing

https://github.com/tranngocphu/opticalflow-activenematics

공식 코드

Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics

https://github.com/tsenst/CrowdFlow

공식 코드

Optical Flow Dataset and Benchmark for Visual Crowd Analysis

https://github.com/tsujuifu/pytorch_empirical-mvm

공식 코드

An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling

https://github.com/ttlzfhy/D-DPCC

공식 코드

D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction

https://github.com/ttlzfhy/LDPCC

공식 코드

Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching

https://github.com/tub-rip/e2fai

공식 코드

Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras

https://github.com/tub-rip/event_based_bos

공식 코드

Event-based Background-Oriented Schlieren

https://github.com/tub-rip/event_based_image_rec_inverse_problem

공식 코드

Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow

https://github.com/tub-rip/event_based_optical_flow

공식 코드

Secrets of Event-Based Optical Flow

https://github.com/tub-rip/motionpriorcmax

공식 코드

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation

https://github.com/tudelft/cuSNN

공식 코드

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception

https://github.com/tudelft/idnet

공식 코드

Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

https://github.com/tum-vision/sublabel_relax

공식 코드

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies

https://github.com/twhui/LiteFlowNet

공식 코드

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation

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