https://github.com/google-research/google-research/tree/master/smurf
공식 코드SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
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/google-research/google-research/tree/master/uflow
공식 코드https://github.com/google-research/kubric
공식 코드https://github.com/google-research/slot-attention-video
공식 코드https://github.com/gorgen2020/hspgnn
공식 코드https://github.com/gorjanradevski/multimodal-distillation
공식 코드https://github.com/gowiththeflowpaper/gowiththeflowpaper.github.io
공식 코드Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
https://github.com/grassknoted/Modified-Two-Stream-Fusion-for-Real-time-ActionRecognition
공식 코드Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset
https://github.com/great-whu/dba-fusion
공식 코드https://github.com/ground-a-video/ground-a-video
공식 코드Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
https://github.com/guangmingw/DOPlearning
공식 코드Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
https://github.com/guoleisun/vss-mrcfa
공식 코드Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation
https://github.com/gurkirt/AMTNet
공식 코드https://github.com/h-deep/trans-svsr
공식 코드A New Dataset and Transformer for Stereoscopic Video Super-Resolution
https://github.com/haesoochung/lan-hdr
공식 코드LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction
https://github.com/halajun/multimot_track
공식 코드https://github.com/halleyjiang/romnistereo
공식 코드https://github.com/hanlingsgjk/unifiedgeneralization
공식 코드https://github.com/hannahhalin/monet
공식 코드https://github.com/haofeixu/flow1d
공식 코드High-Resolution Optical Flow from 1D Attention and Correlation
https://github.com/haofeixu/gmflow
공식 코드https://github.com/harkiratbehl/MetaVOS
공식 코드Meta Learning Deep Visual Words for Fast Video Object Segmentation
https://github.com/hashtag00002/tt-df
공식 코드TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection
https://github.com/hbilen/dynamic-image-nets
공식 코드https://github.com/hellochick/FICM
공식 코드https://github.com/heyuanpengpku/guef
공식 코드https://github.com/highwaywu/st-ddl
공식 코드Exploring Spatial-Temporal Features for Deepfake Detection and Localization
https://github.com/hitottiez/sdof-tracker
공식 코드SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow
https://github.com/hitrainer/eavsr
공식 코드Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution
https://github.com/hmorimitsu/ptlflow
공식 코드DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
https://github.com/hnyu/vonet
공식 코드https://github.com/holmdk/CloudCast
공식 코드CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds
https://github.com/hoyyyaard/3dflowaction
공식 코드3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
https://github.com/hpcforge/bubbleml
공식 코드BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
https://github.com/hsp-iit/fast-ycb
공식 코드ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
https://github.com/hsp-iit/roft
공식 코드ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.