https://github.com/ekgibbons/pytorch-sepconv
공식 코드Implementing Adaptive Separable Convolution for Video Frame Interpolation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The goal of Video Frame Interpolation is to synthesize several frames in the middle of two adjacent frames of the original video. Video Frame Interpolation can be applied to generate slow motion video, increase video frame rate, and frame recovery in video streaming.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Implementing Adaptive Separable Convolution for Video Frame Interpolation
Many-to-many Splatting for Efficient Video Frame Interpolation
Z-upscaling: Optical Flow Guided Frame Interpolation for Isotropic Reconstruction of 3D EM Volumes
WAIT: Feature Warping for Animation to Illustration video Translation using GANs
Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields
MOSO: Decomposing MOtion, Scene and Object for Video Prediction
Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images
Asymmetric Bilateral Motion Estimation for Video Frame Interpolation
Image2Gif: Generating Continuous Realistic Animations with Warping NODEs
Video Frame Interpolation with Densely Queried Bilateral Correlation
GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
Implementing Adaptive Separable Convolution for Video Frame Interpolation
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
Perception-Oriented Video Frame Interpolation via Asymmetric Blending
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.