https://github.com/why986/VFA
공식 코드Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space
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/wish44165/ReynoldsFlow
공식 코드ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem
https://github.com/wjf5203/vnext
공식 코드InstMove: Instance Motion for Object-centric Video Segmentation
https://github.com/wponghiran/temporally_dense_flow
공식 코드Event-based Temporally Dense Optical Flow Estimation with Sequential Learning
https://github.com/wpr1018001/rethinking-low-quality-optical-flow
공식 코드Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow
https://github.com/wrld/free-surgs
공식 코드Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction
https://github.com/wtomin/MIMAMO-Net
공식 코드MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition
https://github.com/wwsource/splatflow
공식 코드https://github.com/wyzjack/mrmga4vad
공식 코드Making Reconstruction-based Method Great Again for Video Anomaly Detection
https://github.com/xiaofeng94/gmflownet
공식 코드Global Matching with Overlapping Attention for Optical Flow Estimation
https://github.com/xiaoqi-zhao-dlut/multi-source-aps-zvos
공식 코드Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
https://github.com/xilin1991/CluterNet
공식 코드Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
https://github.com/xingy038/ds-depth
공식 코드DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
https://github.com/xinyiw915/relax-vqa
공식 코드ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
https://github.com/xinyusun/mme
공식 코드Masked Motion Encoding for Self-Supervised Video Representation Learning
https://github.com/xjpp2016/mavd
공식 코드Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method
https://github.com/xsqhust/turbulence_removal
공식 코드https://github.com/xy-boy/lgtd
공식 코드Local-Global Temporal Difference Learning for Satellite Video Super-Resolution
https://github.com/xy-boy/tdmvsr
공식 코드Local-Global Temporal Difference Learning for Satellite Video Super-Resolution
https://github.com/yanghai-1218/scflow
공식 코드Shape-Constraint Recurrent Flow for 6D Object Pose Estimation
https://github.com/yanglier/ego-motion-estimation
공식 코드https://github.com/yangxy/sdl
공식 코드https://github.com/yaochih/gcvd-release
공식 코드Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training
https://github.com/yaozhuwa/eva-flow
공식 코드https://github.com/yeates/dmt
공식 코드https://github.com/yihengzhang-cv/mcl-motion-focused-contrastive-learning
공식 코드Motion-Focused Contrastive Learning of Video Representations
https://github.com/yingfuxu/ann_vs_snn_evflow
공식 코드https://github.com/yitian97/SDformerFlow
공식 코드SDformerFlow: Spatiotemporal swin spikeformer for event-based optical flow estimation
https://github.com/yjxiong/caffe
공식 코드Real-time Action Recognition with Enhanced Motion Vector CNNs
https://github.com/yjzhang96/UTI-VFI
공식 코드https://github.com/yongleex/diffeomorphicpiv
공식 코드https://github.com/youjie-zhou/fmf-slam
공식 코드https://github.com/yoyo-nb/thin-plate-spline-motion-model
공식 코드https://github.com/yuanmingze/360OpticalFlow-TangentImages
공식 코드https://github.com/yuguangnudt/VEC_VAD
공식 코드Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events
https://github.com/yuhaozhang7/NGD-SLAM
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.