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/twhui/LiteFlowNet2

공식 코드

A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization

https://github.com/twhui/LiteFlowNet3

공식 코드

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

https://github.com/ubc-vision/COTR

공식 코드

COTR: Correspondence Transformer for Matching Across Images

https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose

공식 코드

Bootstrapping Human Optical Flow and Pose

https://github.com/ucbdrive/hd3

공식 코드

Hierarchical Discrete Distribution Decomposition for Match Density Estimation

https://github.com/uncbiag/ICON

공식 코드

$\texttt{GradICON}$: Approximate Diffeomorphisms via Gradient Inverse Consistency

https://github.com/uof1745-cmd/sdp

공식 코드

Spatiotemporal Deformation Perception for Fisheye Video Rectification

https://github.com/ustc-imcl/envc

공식 코드

Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression

https://github.com/uverma/ManipalUAVid

공식 코드

UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

https://github.com/uzh-rpg/e-raft

공식 코드

E-RAFT: Dense Optical Flow from Event Cameras

https://github.com/uzh-rpg/event-based_vision_resources

공식 코드

Event-based Background-Oriented Schlieren

https://github.com/uzh-rpg/rpg_event_representation_learning

공식 코드

End-to-End Learning of Representations for Asynchronous Event-Based Data

https://github.com/uzh-rpg/rpg_timelens

공식 코드

TimeLens: Event-based Video Frame Interpolation

https://github.com/vbrebion/rt_of_low_high_res_event_cameras

공식 코드

Real-Time Optical Flow for Vehicular Perception with Low- and High-Resolution Event Cameras

https://github.com/vdigpku/flownas

공식 코드

FlowNAS: Neural Architecture Search for Optical Flow Estimation

https://github.com/verlab/SemanticFastForward_JVCI_2018

공식 코드

Making a long story short: A Multi-Importance fast-forwarding egocentric videos with the emphasis on relevant objects

https://github.com/vgenai-netflix-eyeline-research/go-with-the-flow

공식 코드

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

https://github.com/vincent-leguen/COMBO

공식 코드

Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction

https://github.com/vincentqqu/evrepsl

공식 코드

EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision

https://github.com/viorik/ConvLSTM

공식 코드

Spatio-temporal video autoencoder with differentiable memory

https://github.com/visinf/irr

공식 코드

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

https://github.com/visinf/ppac_refinement

공식 코드

Probabilistic Pixel-Adaptive Refinement Networks

https://github.com/visinf/self-mono-sf

공식 코드

Self-Supervised Monocular Scene Flow Estimation

https://github.com/visinf/semantic_lattice

공식 코드

Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice

https://github.com/vision-sjtu/usot

공식 코드

Learning to Track Objects from Unlabeled Videos

https://github.com/vlislab22/Deep-Learning-for-Event-based-Vision

공식 코드

Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks

https://github.com/vogechri/CustomNetworkLayers

공식 코드

Learning Energy Based Inpainting for Optical Flow

https://github.com/vt-vl-lab/DF-Net

공식 코드

DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

https://github.com/wang-chen/correlation_flow

공식 코드

Correlation Flow: Robust Optical Flow Using Kernel Cross-Correlators

https://github.com/wangbo-zhao/2022cvpr-mmmmtbvs

공식 코드

Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

https://github.com/wangkaihong/unsup_recycle_gan

공식 코드

Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow

https://github.com/watonomous/action-classification

공식 코드

RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow

https://github.com/weathon/vcos

공식 코드

ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation

https://github.com/weifeng-chen/control-a-video

공식 코드

Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning

https://github.com/weizheliu/People-Flows

공식 코드

Estimating People Flows to Better Count Them in Crowded Scenes

https://github.com/wenz116/drft

공식 코드

End-to-end Multi-modal Video Temporal Grounding

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