https://github.com/yunfan1202/Delving-into-Crispness
공식 코드Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
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/yz93/anchor-diff-VOS
공식 코드https://github.com/yzcjtr/GeoNet
공식 코드GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
https://github.com/yzxing87/pytorch-deep-video-prior
공식 코드https://github.com/zacjiang/GMA
공식 코드Learning to Estimate Hidden Motions with Global Motion Aggregation
https://github.com/zacjiang/scv
공식 코드https://github.com/zcsrenlongz/deblur4dgs
공식 코드Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video
https://github.com/zehuiz2/crackpropnet
공식 코드https://github.com/zhang-can/PAN-PyTorch
공식 코드PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
https://github.com/zhangzjn/DTVNet
공식 코드DTVNet: Dynamic Time-lapse Video Generation via Single Still Image
https://github.com/zhaoxing2022/mmn-vsod
공식 코드Motion-aware Memory Network for Fast Video Salient Object Detection
https://github.com/zhaoxingZ/STVO
공식 코드Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry
https://github.com/zhe-sapi/udass
공식 코드https://github.com/zhonghuayi/focusflow_official
공식 코드FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving
https://github.com/zhonghuayi/optical_flow_robustness_benchmark
공식 코드Benchmarking the Robustness of Optical Flow Estimation to Corruptions
https://github.com/zhu-qianyu/piv-flowdiffuser
공식 코드PIV-FlowDiffuser:Transfer-learning-based denoising diffusion models for PIV
https://github.com/zhujiagang/DTPP
공식 코드End-to-end Video-level Representation Learning for Action Recognition
https://github.com/zihuazheng/dip
공식 코드DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow
https://github.com/zju3dv/PVO
공식 코드https://github.com/zkccz/stbn
공식 코드Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising
https://github.com/zrrr1997/syn2real_dg
공식 코드https://github.com/zwyking/fast-stab
공식 코드Fast Full-frame Video Stabilization with Iterative Optimization
https://github.com/zyzhangustc/mellm
공식 코드MELLM: Exploring LLM-Powered Micro-Expression Understanding Enhanced by Subtle Motion Perception
https://github.com/zzh-tech/animation-from-blur
공식 코드Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
https://github.com/zzh-tech/dual-reversed-rs
공식 코드Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
https://github.com/zzy-zhou/dsec-mos
공식 코드Event-Free Moving Object Segmentation from Moving Ego Vehicle
https://gitlab.com/auxilia/cubes3d
공식 코드Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes
https://zenodo.org/record/3659180
공식 코드Predictive online optimisation with applications to optical flow
https://github.com/2023-MindSpore-1/ms-code-10/tree/main/ms-code-10/PWCNet
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
https://github.com/2023-MindSpore-1/ms-code-211/tree/main/dgcnet_res101
https://github.com/2023-MindSpore-1/ms-code-213/tree/main/fastflow
FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
https://github.com/2023-MindSpore-1/ms-code-214/tree/main/flownet2
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
https://github.com/2023-MindSpore-1/ms-code-215/tree/main/PoseNet
Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
https://github.com/2023-MindSpore-1/ms-code-36
https://github.com/2023-MindSpore-4/Code10/tree/main/flownet2
https://github.com/2023-MindSpore-4/Code12/tree/main/liliang/ssa
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.